From 99222c9e4de7feb22c93b19a92b35fcdad73ed42 Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Thu, 7 Jan 2016 20:17:33 +0800 Subject: [PATCH 001/489] clk: rockchip: rk3036: fix the FLAGs for clock mux The DFLAGS are used for the clock dividers, the CLKSEL_CON flags of COMPOSITE_NODIV type should be MFLAGS. Signed-off-by: Xing Zheng Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3036.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c index ebce98033fbb..7e3b41cd3e5b 100644 --- a/drivers/clk/rockchip/clk-rk3036.c +++ b/drivers/clk/rockchip/clk-rk3036.c @@ -224,16 +224,16 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = { RK2928_CLKGATE_CON(2), 2, GFLAGS), COMPOSITE_NODIV(SCLK_TIMER0, "sclk_timer0", mux_timer_p, CLK_IGNORE_UNUSED, - RK2928_CLKSEL_CON(2), 4, 1, DFLAGS, + RK2928_CLKSEL_CON(2), 4, 1, MFLAGS, RK2928_CLKGATE_CON(1), 0, GFLAGS), COMPOSITE_NODIV(SCLK_TIMER1, "sclk_timer1", mux_timer_p, CLK_IGNORE_UNUSED, - RK2928_CLKSEL_CON(2), 5, 1, DFLAGS, + RK2928_CLKSEL_CON(2), 5, 1, MFLAGS, RK2928_CLKGATE_CON(1), 1, GFLAGS), COMPOSITE_NODIV(SCLK_TIMER2, "sclk_timer2", mux_timer_p, CLK_IGNORE_UNUSED, - RK2928_CLKSEL_CON(2), 6, 1, DFLAGS, + RK2928_CLKSEL_CON(2), 6, 1, MFLAGS, RK2928_CLKGATE_CON(2), 4, GFLAGS), COMPOSITE_NODIV(SCLK_TIMER3, "sclk_timer3", mux_timer_p, CLK_IGNORE_UNUSED, - RK2928_CLKSEL_CON(2), 7, 1, DFLAGS, + RK2928_CLKSEL_CON(2), 7, 1, MFLAGS, RK2928_CLKGATE_CON(2), 5, GFLAGS), MUX(0, "uart_pll_clk", mux_pll_src_apll_dpll_gpll_usb480m_p, 0, @@ -279,13 +279,13 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = { RK2928_CLKGATE_CON(3), 2, GFLAGS), COMPOSITE_NODIV(0, "sclk_sdmmc_src", mux_mmc_src_p, 0, - RK2928_CLKSEL_CON(12), 8, 2, DFLAGS, + RK2928_CLKSEL_CON(12), 8, 2, MFLAGS, RK2928_CLKGATE_CON(2), 11, GFLAGS), DIV(SCLK_SDMMC, "sclk_sdmmc", "sclk_sdmmc_src", 0, RK2928_CLKSEL_CON(11), 0, 7, DFLAGS), COMPOSITE_NODIV(0, "sclk_sdio_src", mux_mmc_src_p, 0, - RK2928_CLKSEL_CON(12), 10, 2, DFLAGS, + RK2928_CLKSEL_CON(12), 10, 2, MFLAGS, RK2928_CLKGATE_CON(2), 13, GFLAGS), DIV(SCLK_SDIO, "sclk_sdio", "sclk_sdio_src", 0, RK2928_CLKSEL_CON(11), 8, 7, DFLAGS), From b29de2de5049e064d172862b1feeddeb650c3ee8 Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Thu, 7 Jan 2016 20:17:34 +0800 Subject: [PATCH 002/489] clk: rockchip: rk3036: fix uarts clock error Due to a copy-paste error the uart1 and uart2 clock div set incorrect, fix it. Signed-off-by: Xing Zheng Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3036.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c index 7e3b41cd3e5b..04b5249bcf0b 100644 --- a/drivers/clk/rockchip/clk-rk3036.c +++ b/drivers/clk/rockchip/clk-rk3036.c @@ -242,11 +242,11 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = { RK2928_CLKSEL_CON(13), 0, 7, DFLAGS, RK2928_CLKGATE_CON(1), 8, GFLAGS), COMPOSITE_NOMUX(0, "uart1_src", "uart_pll_clk", 0, - RK2928_CLKSEL_CON(13), 0, 7, DFLAGS, - RK2928_CLKGATE_CON(1), 8, GFLAGS), + RK2928_CLKSEL_CON(14), 0, 7, DFLAGS, + RK2928_CLKGATE_CON(1), 10, GFLAGS), COMPOSITE_NOMUX(0, "uart2_src", "uart_pll_clk", 0, - RK2928_CLKSEL_CON(13), 0, 7, DFLAGS, - RK2928_CLKGATE_CON(1), 8, GFLAGS), + RK2928_CLKSEL_CON(15), 0, 7, DFLAGS, + RK2928_CLKGATE_CON(1), 12, GFLAGS), COMPOSITE_FRACMUX(0, "uart0_frac", "uart0_src", CLK_SET_RATE_PARENT, RK2928_CLKSEL_CON(17), 0, RK2928_CLKGATE_CON(1), 9, GFLAGS, From c40519350e1d7db03e35e57509352c55948648ba Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Thu, 7 Jan 2016 20:17:35 +0800 Subject: [PATCH 003/489] clk: rockchip: rk3036: fix the div offset for emac clock Due to reference to old version TRM, there are incorrect emac clock node. The SEL_21_9 is used for the parent div, the SEL_21_4 is used for the child div. Signed-off-by: Xing Zheng Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3036.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c index 04b5249bcf0b..1f00fab72dfb 100644 --- a/drivers/clk/rockchip/clk-rk3036.c +++ b/drivers/clk/rockchip/clk-rk3036.c @@ -344,12 +344,12 @@ static struct rockchip_clk_branch rk3036_clk_branches[] __initdata = { RK2928_CLKGATE_CON(10), 5, GFLAGS), COMPOSITE_NOGATE(0, "mac_pll_src", mux_pll_src_3plls_p, 0, - RK2928_CLKSEL_CON(21), 0, 2, MFLAGS, 4, 5, DFLAGS), + RK2928_CLKSEL_CON(21), 0, 2, MFLAGS, 9, 5, DFLAGS), MUX(SCLK_MACREF, "mac_clk_ref", mux_mac_p, CLK_SET_RATE_PARENT, RK2928_CLKSEL_CON(21), 3, 1, MFLAGS), COMPOSITE_NOMUX(SCLK_MAC, "mac_clk", "mac_clk_ref", 0, - RK2928_CLKSEL_CON(21), 9, 5, DFLAGS, + RK2928_CLKSEL_CON(21), 4, 5, DFLAGS, RK2928_CLKGATE_CON(2), 6, GFLAGS), MUX(SCLK_HDMI, "dclk_hdmi", mux_dclk_p, 0, From 3d667920bc8fc0c3b39e4e740352d9367fa4916e Mon Sep 17 00:00:00 2001 From: Xing Zheng Date: Thu, 7 Jan 2016 20:17:36 +0800 Subject: [PATCH 004/489] clk: rockchip: rk3036: rename emac ext source clock There is only support rmii in the RK3036, so we should use the correct ext clock name as described in the TRM. Signed-off-by: Xing Zheng [update dt-binding document as well] Signed-off-by: Heiko Stuebner --- Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt | 2 +- drivers/clk/rockchip/clk-rk3036.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt index ace05992a262..20df350b9ef3 100644 --- a/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt +++ b/Documentation/devicetree/bindings/clock/rockchip,rk3036-cru.txt @@ -30,7 +30,7 @@ that they are defined using standard clock bindings with following clock-output-names: - "xin24m" - crystal input - required, - "ext_i2s" - external I2S clock - optional, - - "ext_gmac" - external GMAC clock - optional + - "rmii_clkin" - external EMAC clock - optional Example: Clock controller node: diff --git a/drivers/clk/rockchip/clk-rk3036.c b/drivers/clk/rockchip/clk-rk3036.c index 1f00fab72dfb..bc7fbac83ab7 100644 --- a/drivers/clk/rockchip/clk-rk3036.c +++ b/drivers/clk/rockchip/clk-rk3036.c @@ -133,7 +133,7 @@ PNAME(mux_spdif_p) = { "spdif_src", "spdif_frac", "xin12m" }; PNAME(mux_uart0_p) = { "uart0_src", "uart0_frac", "xin24m" }; PNAME(mux_uart1_p) = { "uart1_src", "uart1_frac", "xin24m" }; PNAME(mux_uart2_p) = { "uart2_src", "uart2_frac", "xin24m" }; -PNAME(mux_mac_p) = { "mac_pll_src", "ext_gmac" }; +PNAME(mux_mac_p) = { "mac_pll_src", "rmii_clkin" }; PNAME(mux_dclk_p) = { "dclk_lcdc", "dclk_cru" }; static struct rockchip_pll_clock rk3036_pll_clks[] __initdata = { From 8931f8e02979e4180566907019d432527c80abf7 Mon Sep 17 00:00:00 2001 From: Jianqun xu Date: Thu, 7 Jan 2016 17:18:07 +0800 Subject: [PATCH 005/489] clk: rockchip: rk3368: fix some clock gates Reference to the Rockchip RK3368 TRM v1.1, some clock gates need to be updated. Signed-off-by: Jianqun xu Signed-off-by: Caesar Wang Signed-off-by: Heiko Stuebner --- drivers/clk/rockchip/clk-rk3368.c | 26 +++++++++++++------------- 1 file changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c index be0ede522269..21f3ea909fab 100644 --- a/drivers/clk/rockchip/clk-rk3368.c +++ b/drivers/clk/rockchip/clk-rk3368.c @@ -780,13 +780,13 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { GATE(PCLK_TSADC, "pclk_tsadc", "pclk_peri", 0, RK3368_CLKGATE_CON(20), 0, GFLAGS), /* pclk_pd_alive gates */ - GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 8, GFLAGS), - GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 7, GFLAGS), - GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 12, GFLAGS), - GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 11, GFLAGS), - GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 3, GFLAGS), - GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 2, GFLAGS), - GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(14), 1, GFLAGS), + GATE(PCLK_TIMER1, "pclk_timer1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 13, GFLAGS), + GATE(PCLK_TIMER0, "pclk_timer0", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 12, GFLAGS), + GATE(0, "pclk_alive_niu", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(22), 9, GFLAGS), + GATE(PCLK_GRF, "pclk_grf", "pclk_pd_alive", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(22), 8, GFLAGS), + GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 3, GFLAGS), + GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 2, GFLAGS), + GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_pd_alive", 0, RK3368_CLKGATE_CON(22), 1, GFLAGS), /* * pclk_vio gates @@ -796,12 +796,12 @@ static struct rockchip_clk_branch rk3368_clk_branches[] __initdata = { GATE(0, "pclk_dphytx", "hclk_vio", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(14), 8, GFLAGS), /* pclk_pd_pmu gates */ - GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 0, GFLAGS), - GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(17), 4, GFLAGS), - GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 3, GFLAGS), - GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS), - GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 1, GFLAGS), - GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(17), 2, GFLAGS), + GATE(PCLK_PMUGRF, "pclk_pmugrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 5, GFLAGS), + GATE(PCLK_GPIO0, "pclk_gpio0", "pclk_pd_pmu", 0, RK3368_CLKGATE_CON(23), 4, GFLAGS), + GATE(PCLK_SGRF, "pclk_sgrf", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 3, GFLAGS), + GATE(0, "pclk_pmu_noc", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 2, GFLAGS), + GATE(0, "pclk_intmem1", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 1, GFLAGS), + GATE(PCLK_PMU, "pclk_pmu", "pclk_pd_pmu", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(23), 0, GFLAGS), /* timer gates */ GATE(0, "sclk_timer15", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 11, GFLAGS), From 383bf44d1a8b18de5c26ec2a48c6822681b50984 Mon Sep 17 00:00:00 2001 From: Miroslav Benes Date: Thu, 14 Jan 2016 11:35:53 +0100 Subject: [PATCH 006/489] livepatch: change the error message in asm/livepatch.h header files If anyone includes asm/livepatch.h when CONFIG_LIVEPATCH=n the build fails with the existing error message. Change it to something saner. [jkosina@suse.cz: fixed changelog typo spotted by Josh] Suggested-by: Andrew Morton Signed-off-by: Miroslav Benes Acked-by: Josh Poimboeuf Signed-off-by: Jiri Kosina --- arch/s390/include/asm/livepatch.h | 2 +- arch/x86/include/asm/livepatch.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/s390/include/asm/livepatch.h b/arch/s390/include/asm/livepatch.h index 7aa799134a11..a52b6cca873d 100644 --- a/arch/s390/include/asm/livepatch.h +++ b/arch/s390/include/asm/livepatch.h @@ -37,7 +37,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) regs->psw.addr = ip; } #else -#error Live patching support is disabled; check CONFIG_LIVEPATCH +#error Include linux/livepatch.h, not asm/livepatch.h #endif #endif diff --git a/arch/x86/include/asm/livepatch.h b/arch/x86/include/asm/livepatch.h index 19c099afa861..e795f5274217 100644 --- a/arch/x86/include/asm/livepatch.h +++ b/arch/x86/include/asm/livepatch.h @@ -41,7 +41,7 @@ static inline void klp_arch_set_pc(struct pt_regs *regs, unsigned long ip) regs->ip = ip; } #else -#error Live patching support is disabled; check CONFIG_LIVEPATCH +#error Include linux/livepatch.h, not asm/livepatch.h #endif #endif /* _ASM_X86_LIVEPATCH_H */ From 21e4903246029e221ee92e3be3653f2805fac898 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Thu, 14 Jan 2016 14:24:30 -0500 Subject: [PATCH 007/489] clk: tegra: Fix divider on VI_I2C VI-I2C has 16 bits available for its divider. Switch the divider width to 16 instead of 8 so correct rates can be set. Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra-periph.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c index 6ad381a888a6..105405ca85ab 100644 --- a/drivers/clk/tegra/clk-tegra-periph.c +++ b/drivers/clk/tegra/clk-tegra-periph.c @@ -782,7 +782,7 @@ static struct tegra_periph_init_data periph_clks[] = { NODIV("sor1", mux_clkm_sor1_brick_sor1_src, CLK_SOURCE_SOR1, 15, MASK(1), 183, 0, tegra_clk_sor1, &sor1_lock), MUX8("sdmmc_legacy", mux_pllp_out3_clkm_pllp_pllc4, CLK_SOURCE_SDMMC_LEGACY, 193, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_sdmmc_legacy), MUX8("qspi", mux_pllp_pllc_pllc_out1_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_QSPI, 211, TEGRA_PERIPH_ON_APB, tegra_clk_qspi), - MUX("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, TEGRA_PERIPH_ON_APB, tegra_clk_vi_i2c), + I2C("vii2c", mux_pllp_pllc_clkm, CLK_SOURCE_VI_I2C, 208, tegra_clk_vi_i2c), MUX("mipibif", mux_pllp_clkm, CLK_SOURCE_MIPIBIF, 173, TEGRA_PERIPH_ON_APB, tegra_clk_mipibif), MUX("uartape", mux_pllp_pllc_clkm, CLK_SOURCE_UARTAPE, 212, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_uartape), MUX8("tsecb", mux_pllp_pllc2_c_c3_clkm, CLK_SOURCE_TSECB, 206, 0, tegra_clk_tsecb), From 14050118afee4d8bd81d22fefa3e986172b08bc6 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Thu, 14 Jan 2016 14:24:31 -0500 Subject: [PATCH 008/489] clk: tegra: Remove improper flags for lock_enable Most PLL's don't actually have LOCK_ENABLE bits. However, most PLL's also had that flag set, which meant that the clk code was trying to enable locks, and inadvertantly flipping bits in other fields. For PLLM, ensure the correct register is used for the misc_register. PLL_MISC0 contains the EN_LCKDET bit which should be used for enabling the lock, and PLLM_MISC1 shouldn't be used at all. Lastly, remove some of the settings which would point to the EN_LCKDET bits for some PLLs. There is no need to enable the locks, and that is done as part of the set_defaults logic already. Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 42 +++++++++++--------------------- 1 file changed, 14 insertions(+), 28 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 58514c44ea83..f45c9adf7fb2 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -1386,7 +1386,7 @@ static struct tegra_clk_pll_params pll_c_params = { .mdiv_default = 3, .div_nmp = &pllc_nmp, .freq_table = pll_cx_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .set_defaults = _pllc_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1425,7 +1425,7 @@ static struct tegra_clk_pll_params pll_c2_params = { .ext_misc_reg[2] = PLLC2_MISC2, .ext_misc_reg[3] = PLLC2_MISC3, .freq_table = pll_cx_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .set_defaults = _pllc2_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1455,7 +1455,7 @@ static struct tegra_clk_pll_params pll_c3_params = { .ext_misc_reg[2] = PLLC3_MISC2, .ext_misc_reg[3] = PLLC3_MISC3, .freq_table = pll_cx_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .set_defaults = _pllc3_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1505,7 +1505,6 @@ static struct tegra_clk_pll_params pll_c4_vco_params = { .base_reg = PLLC4_BASE, .misc_reg = PLLC4_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE, .lock_delay = 300, .max_p = PLL_QLIN_PDIV_MAX, .ext_misc_reg[0] = PLLC4_MISC0, @@ -1517,8 +1516,7 @@ static struct tegra_clk_pll_params pll_c4_vco_params = { .div_nmp = &pllss_nmp, .freq_table = pll_c4_vco_freq_table, .set_defaults = tegra210_pllc4_set_defaults, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE | - TEGRA_PLL_VCO_OUT, + .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1559,7 +1557,7 @@ static struct tegra_clk_pll_params pll_m_params = { .vco_min = 800000000, .vco_max = 1866000000, .base_reg = PLLM_BASE, - .misc_reg = PLLM_MISC1, + .misc_reg = PLLM_MISC0, .lock_mask = PLL_BASE_LOCK, .lock_enable_bit_idx = PLLM_MISC_LOCK_ENABLE, .lock_delay = 300, @@ -1588,7 +1586,6 @@ static struct tegra_clk_pll_params pll_mb_params = { .base_reg = PLLMB_BASE, .misc_reg = PLLMB_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLMB_MISC_LOCK_ENABLE, .lock_delay = 300, .iddq_reg = PLLMB_MISC0, .iddq_bit_idx = PLLMB_IDDQ_BIT, @@ -1598,7 +1595,7 @@ static struct tegra_clk_pll_params pll_mb_params = { .pdiv_tohw = pll_qlin_pdiv_to_hw, .div_nmp = &pllm_nmp, .freq_table = pll_m_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .set_defaults = tegra210_pllmb_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1671,7 +1668,6 @@ static struct tegra_clk_pll_params pll_re_vco_params = { .base_reg = PLLRE_BASE, .misc_reg = PLLRE_MISC0, .lock_mask = PLLRE_MISC_LOCK, - .lock_enable_bit_idx = PLLRE_MISC_LOCK_ENABLE, .lock_delay = 300, .max_p = PLL_QLIN_PDIV_MAX, .ext_misc_reg[0] = PLLRE_MISC0, @@ -1681,8 +1677,7 @@ static struct tegra_clk_pll_params pll_re_vco_params = { .pdiv_tohw = pll_qlin_pdiv_to_hw, .div_nmp = &pllre_nmp, .freq_table = pll_re_vco_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_LOCK_MISC | - TEGRA_PLL_HAS_LOCK_ENABLE | TEGRA_PLL_VCO_OUT, + .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_LOCK_MISC | TEGRA_PLL_VCO_OUT, .set_defaults = tegra210_pllre_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1712,7 +1707,6 @@ static struct tegra_clk_pll_params pll_p_params = { .base_reg = PLLP_BASE, .misc_reg = PLLP_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLP_MISC_LOCK_ENABLE, .lock_delay = 300, .iddq_reg = PLLP_MISC0, .iddq_bit_idx = PLLXP_IDDQ_BIT, @@ -1721,8 +1715,7 @@ static struct tegra_clk_pll_params pll_p_params = { .div_nmp = &pllp_nmp, .freq_table = pll_p_freq_table, .fixed_rate = 408000000, - .flags = TEGRA_PLL_FIXED | TEGRA_PLL_USE_LOCK | - TEGRA_PLL_HAS_LOCK_ENABLE | TEGRA_PLL_VCO_OUT, + .flags = TEGRA_PLL_FIXED | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT, .set_defaults = tegra210_pllp_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1750,7 +1743,7 @@ static struct tegra_clk_pll_params pll_a1_params = { .ext_misc_reg[2] = PLLA1_MISC2, .ext_misc_reg[3] = PLLA1_MISC3, .freq_table = pll_cx_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .set_defaults = _plla1_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; @@ -1787,7 +1780,6 @@ static struct tegra_clk_pll_params pll_a_params = { .base_reg = PLLA_BASE, .misc_reg = PLLA_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLA_MISC_LOCK_ENABLE, .lock_delay = 300, .round_p_to_pdiv = pll_qlin_p_to_pdiv, .pdiv_tohw = pll_qlin_pdiv_to_hw, @@ -1802,8 +1794,7 @@ static struct tegra_clk_pll_params pll_a_params = { .ext_misc_reg[1] = PLLA_MISC1, .ext_misc_reg[2] = PLLA_MISC2, .freq_table = pll_a_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_MDIV_NEW | - TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK | TEGRA_MDIV_NEW, .set_defaults = tegra210_plla_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, .set_gain = tegra210_clk_pll_set_gain, @@ -1836,7 +1827,6 @@ static struct tegra_clk_pll_params pll_d_params = { .base_reg = PLLD_BASE, .misc_reg = PLLD_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLD_MISC_LOCK_ENABLE, .lock_delay = 1000, .iddq_reg = PLLD_MISC0, .iddq_bit_idx = PLLD_IDDQ_BIT, @@ -1850,7 +1840,7 @@ static struct tegra_clk_pll_params pll_d_params = { .ext_misc_reg[0] = PLLD_MISC0, .ext_misc_reg[1] = PLLD_MISC1, .freq_table = pll_d_freq_table, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .mdiv_default = 1, .set_defaults = tegra210_plld_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, @@ -1876,7 +1866,6 @@ static struct tegra_clk_pll_params pll_d2_params = { .base_reg = PLLD2_BASE, .misc_reg = PLLD2_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE, .lock_delay = 300, .iddq_reg = PLLD2_BASE, .iddq_bit_idx = PLLSS_IDDQ_BIT, @@ -1897,7 +1886,7 @@ static struct tegra_clk_pll_params pll_d2_params = { .mdiv_default = 1, .freq_table = tegra210_pll_d2_freq_table, .set_defaults = tegra210_plld2_set_defaults, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .calc_rate = tegra210_pll_fixed_mdiv_cfg, .set_gain = tegra210_clk_pll_set_gain, .adjust_vco = tegra210_clk_adjust_vco_min, @@ -1920,7 +1909,6 @@ static struct tegra_clk_pll_params pll_dp_params = { .base_reg = PLLDP_BASE, .misc_reg = PLLDP_MISC, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLSS_MISC_LOCK_ENABLE, .lock_delay = 300, .iddq_reg = PLLDP_BASE, .iddq_bit_idx = PLLSS_IDDQ_BIT, @@ -1941,7 +1929,7 @@ static struct tegra_clk_pll_params pll_dp_params = { .mdiv_default = 1, .freq_table = pll_dp_freq_table, .set_defaults = tegra210_plldp_set_defaults, - .flags = TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE, + .flags = TEGRA_PLL_USE_LOCK, .calc_rate = tegra210_pll_fixed_mdiv_cfg, .set_gain = tegra210_clk_pll_set_gain, .adjust_vco = tegra210_clk_adjust_vco_min, @@ -1973,7 +1961,6 @@ static struct tegra_clk_pll_params pll_u_vco_params = { .base_reg = PLLU_BASE, .misc_reg = PLLU_MISC0, .lock_mask = PLL_BASE_LOCK, - .lock_enable_bit_idx = PLLU_MISC_LOCK_ENABLE, .lock_delay = 1000, .iddq_reg = PLLU_MISC0, .iddq_bit_idx = PLLU_IDDQ_BIT, @@ -1983,8 +1970,7 @@ static struct tegra_clk_pll_params pll_u_vco_params = { .pdiv_tohw = pll_qlin_pdiv_to_hw, .div_nmp = &pllu_nmp, .freq_table = pll_u_freq_table, - .flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_HAS_LOCK_ENABLE | - TEGRA_PLL_VCO_OUT, + .flags = TEGRA_PLLU | TEGRA_PLL_USE_LOCK | TEGRA_PLL_VCO_OUT, .set_defaults = tegra210_pllu_set_defaults, .calc_rate = tegra210_pll_fixed_mdiv_cfg, }; From 3a5242e648a8d009f0e0fd47867592e5265374b6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Sun, 24 Jan 2016 04:25:13 +0900 Subject: [PATCH 009/489] pinctrl: pxa: export pxa2xx_pinctrl_init() Building pinctrl-pxa27x.c as a module causes a link error: ERROR: "pxa2xx_pinctrl_init" [drivers/pinctrl/pxa/pinctrl-pxa27x.ko] undefined! Signed-off-by: Masahiro Yamada Acked-by: Robert Jarzmik Signed-off-by: Linus Walleij --- drivers/pinctrl/pxa/pinctrl-pxa2xx.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c index d90e205cf809..216f227c6009 100644 --- a/drivers/pinctrl/pxa/pinctrl-pxa2xx.c +++ b/drivers/pinctrl/pxa/pinctrl-pxa2xx.c @@ -426,6 +426,7 @@ int pxa2xx_pinctrl_init(struct platform_device *pdev, return 0; } +EXPORT_SYMBOL(pxa2xx_pinctrl_init); int pxa2xx_pinctrl_exit(struct platform_device *pdev) { From f5d0ca224a071d7077bbdae347cb514949d64fd9 Mon Sep 17 00:00:00 2001 From: Lucas Stach Date: Tue, 12 Jan 2016 15:04:30 +0100 Subject: [PATCH 010/489] ARM: dts: imx6: remove bogus interrupt-parent from CAAM node The interrupt-parent property is not needed as it is inherited from the parent bus and in the case of the CAAM node actively points to the wrong interrupt controller (GIC instead of GPC). This leads to the CAAM IRQs not getting unmasked at the GPC level, leaving them unable to wake the CPU from wait mode, potentially impacting performance of the CAAM unit when CPUidle is enabled. Signed-off-by: Lucas Stach Signed-off-by: Shawn Guo --- arch/arm/boot/dts/imx6qdl.dtsi | 1 - 1 file changed, 1 deletion(-) diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi index 4f6ae921656f..f74d3db4846d 100644 --- a/arch/arm/boot/dts/imx6qdl.dtsi +++ b/arch/arm/boot/dts/imx6qdl.dtsi @@ -896,7 +896,6 @@ #size-cells = <1>; reg = <0x2100000 0x10000>; ranges = <0 0x2100000 0x10000>; - interrupt-parent = <&intc>; clocks = <&clks IMX6QDL_CLK_CAAM_MEM>, <&clks IMX6QDL_CLK_CAAM_ACLK>, <&clks IMX6QDL_CLK_CAAM_IPG>, From 39178bb2b3e78cfcb9b6311fa9e2b8d6e3cfe51f Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 25 Jan 2016 16:59:09 +0100 Subject: [PATCH 011/489] pinctrl: nomadik: hide unused functions The nomadik pinctrl driver has two functions that are only used for debugfs output and are otherwise unused: drivers/pinctrl/nomadik/pinctrl-abx500.c:194:12: error: 'abx500_get_pull_updown' defined but not used drivers/pinctrl/nomadik/pinctrl-abx500.c:471:12: error: 'abx500_get_mode' defined but not used This makes the function definitions conditional to avoid the harmless warnings. Signed-off-by: Arnd Bergmann Signed-off-by: Linus Walleij --- drivers/pinctrl/nomadik/pinctrl-abx500.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c index 085e60106ec2..1f7469c9857d 100644 --- a/drivers/pinctrl/nomadik/pinctrl-abx500.c +++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c @@ -191,6 +191,7 @@ static void abx500_gpio_set(struct gpio_chip *chip, unsigned offset, int val) dev_err(pct->dev, "%s write failed (%d)\n", __func__, ret); } +#ifdef CONFIG_DEBUG_FS static int abx500_get_pull_updown(struct abx500_pinctrl *pct, int offset, enum abx500_gpio_pull_updown *pull_updown) { @@ -226,6 +227,7 @@ out: return ret; } +#endif static int abx500_set_pull_updown(struct abx500_pinctrl *pct, int offset, enum abx500_gpio_pull_updown val) @@ -468,6 +470,7 @@ out: return ret; } +#ifdef CONFIG_DEBUG_FS static int abx500_get_mode(struct pinctrl_dev *pctldev, struct gpio_chip *chip, unsigned gpio) { @@ -553,8 +556,6 @@ out: return ret; } -#ifdef CONFIG_DEBUG_FS - #include static void abx500_gpio_dbg_show_one(struct seq_file *s, From 1ce133ec89027dc2dff6d0784564da27f1c21fdc Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 8 Jan 2016 09:35:58 -0800 Subject: [PATCH 012/489] clk: mvebu: Mark ioremapped memory as __iomem Silence the following sparse warning drivers/clk/mvebu/dove-divider.c:252:14: warning: incorrect type in assignment (different address spaces) drivers/clk/mvebu/dove-divider.c:252:14: expected void *base drivers/clk/mvebu/dove-divider.c:252:14: got void [noderef] * drivers/clk/mvebu/dove-divider.c:256:13: warning: incorrect type in argument 2 (different address spaces) drivers/clk/mvebu/dove-divider.c:256:13: expected void [noderef] *base drivers/clk/mvebu/dove-divider.c:256:13: got void *base drivers/clk/mvebu/dove-divider.c:257:25: warning: incorrect type in argument 1 (different address spaces) drivers/clk/mvebu/dove-divider.c:257:25: expected void volatile [noderef] *iomem_cookie drivers/clk/mvebu/dove-divider.c:257:25: got void *base Cc: Russell King Signed-off-by: Stephen Boyd --- drivers/clk/mvebu/dove-divider.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/mvebu/dove-divider.c b/drivers/clk/mvebu/dove-divider.c index d5c5bfa35a5a..3e0b52daa35f 100644 --- a/drivers/clk/mvebu/dove-divider.c +++ b/drivers/clk/mvebu/dove-divider.c @@ -247,7 +247,7 @@ static struct clk_onecell_data dove_divider_data = { void __init dove_divider_clk_init(struct device_node *np) { - void *base; + void __iomem *base; base = of_iomap(np, 0); if (WARN_ON(!base)) From d22eb66b3cc3d7d486bc9fa8c6fdbce197eede5f Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Fri, 4 Dec 2015 14:51:36 +0800 Subject: [PATCH 013/489] clk: scpi: Fix checking return value of platform_device_register_simple() platform_device_register_simple() returns ERR_PTR on error. Signed-off-by: Axel Lin Signed-off-by: Stephen Boyd --- drivers/clk/clk-scpi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/clk-scpi.c b/drivers/clk/clk-scpi.c index cd0f2726f5e0..89e9ca78bb94 100644 --- a/drivers/clk/clk-scpi.c +++ b/drivers/clk/clk-scpi.c @@ -299,7 +299,7 @@ static int scpi_clocks_probe(struct platform_device *pdev) /* Add the virtual cpufreq device */ cpufreq_dev = platform_device_register_simple("scpi-cpufreq", -1, NULL, 0); - if (!cpufreq_dev) + if (IS_ERR(cpufreq_dev)) pr_warn("unable to register cpufreq device"); return 0; From eac2d86d60449bc9852f94853cc156897fe9e893 Mon Sep 17 00:00:00 2001 From: Marc Gonzalez Date: Fri, 29 Jan 2016 15:07:22 +0100 Subject: [PATCH 014/489] clk: tango4: rename ARCH_TANGOX to ARCH_TANGO Requested by arm-soc maintainer Kevin Hilman in v9 review. http://article.gmane.org/gmane.linux.ports.arm.kernel/456331 Signed-off-by: Marc Gonzalez Signed-off-by: Stephen Boyd --- drivers/clk/Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile index b038e3666058..bae4be6501df 100644 --- a/drivers/clk/Makefile +++ b/drivers/clk/Makefile @@ -43,7 +43,7 @@ obj-$(CONFIG_COMMON_CLK_SI514) += clk-si514.o obj-$(CONFIG_COMMON_CLK_SI570) += clk-si570.o obj-$(CONFIG_COMMON_CLK_CDCE925) += clk-cdce925.o obj-$(CONFIG_ARCH_STM32) += clk-stm32f4.o -obj-$(CONFIG_ARCH_TANGOX) += clk-tango4.o +obj-$(CONFIG_ARCH_TANGO) += clk-tango4.o obj-$(CONFIG_CLK_TWL6040) += clk-twl6040.o obj-$(CONFIG_ARCH_U300) += clk-u300.o obj-$(CONFIG_ARCH_VT8500) += clk-vt8500.o From 3db70a853202c252a8ebefa71ccb088ad149cdd2 Mon Sep 17 00:00:00 2001 From: Bob Liu Date: Wed, 25 Nov 2015 17:52:55 -0500 Subject: [PATCH 015/489] xen/blkfront: realloc ring info in blkif_resume Need to reallocate ring info in the resume path, because info->rinfo was freed in blkif_free(). And 'multi-queue-max-queues' backend reports may have been changed. Signed-off-by: Bob Liu Reported-and-Tested-by: Konrad Rzeszutek Wilk Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 74 ++++++++++++++++++++++-------------- 1 file changed, 45 insertions(+), 29 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 8a8dc91c39f7..83eb9e6bf8b0 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1873,6 +1873,43 @@ again: return err; } +static int negotiate_mq(struct blkfront_info *info) +{ + unsigned int backend_max_queues = 0; + int err; + unsigned int i; + + BUG_ON(info->nr_rings); + + /* Check if backend supports multiple queues. */ + err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, + "multi-queue-max-queues", "%u", &backend_max_queues); + if (err < 0) + backend_max_queues = 1; + + info->nr_rings = min(backend_max_queues, xen_blkif_max_queues); + /* We need at least one ring. */ + if (!info->nr_rings) + info->nr_rings = 1; + + info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL); + if (!info->rinfo) { + xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); + return -ENOMEM; + } + + for (i = 0; i < info->nr_rings; i++) { + struct blkfront_ring_info *rinfo; + + rinfo = &info->rinfo[i]; + INIT_LIST_HEAD(&rinfo->indirect_pages); + INIT_LIST_HEAD(&rinfo->grants); + rinfo->dev_info = info; + INIT_WORK(&rinfo->work, blkif_restart_queue); + spin_lock_init(&rinfo->ring_lock); + } + return 0; +} /** * Entry point to this code when a new device is created. Allocate the basic * structures and the ring buffer for communication with the backend, and @@ -1883,9 +1920,7 @@ static int blkfront_probe(struct xenbus_device *dev, const struct xenbus_device_id *id) { int err, vdevice; - unsigned int r_index; struct blkfront_info *info; - unsigned int backend_max_queues = 0; /* FIXME: Use dynamic device id if this is not set. */ err = xenbus_scanf(XBT_NIL, dev->nodename, @@ -1936,33 +1971,10 @@ static int blkfront_probe(struct xenbus_device *dev, } info->xbdev = dev; - /* Check if backend supports multiple queues. */ - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "multi-queue-max-queues", "%u", &backend_max_queues); - if (err < 0) - backend_max_queues = 1; - - info->nr_rings = min(backend_max_queues, xen_blkif_max_queues); - /* We need at least one ring. */ - if (!info->nr_rings) - info->nr_rings = 1; - - info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL); - if (!info->rinfo) { - xenbus_dev_fatal(dev, -ENOMEM, "allocating ring_info structure"); + err = negotiate_mq(info); + if (err) { kfree(info); - return -ENOMEM; - } - - for (r_index = 0; r_index < info->nr_rings; r_index++) { - struct blkfront_ring_info *rinfo; - - rinfo = &info->rinfo[r_index]; - INIT_LIST_HEAD(&rinfo->indirect_pages); - INIT_LIST_HEAD(&rinfo->grants); - rinfo->dev_info = info; - INIT_WORK(&rinfo->work, blkif_restart_queue); - spin_lock_init(&rinfo->ring_lock); + return err; } mutex_init(&info->mutex); @@ -2123,12 +2135,16 @@ static int blkif_recover(struct blkfront_info *info) static int blkfront_resume(struct xenbus_device *dev) { struct blkfront_info *info = dev_get_drvdata(&dev->dev); - int err; + int err = 0; dev_dbg(&dev->dev, "blkfront_resume: %s\n", dev->nodename); blkif_free(info, info->connected == BLKIF_STATE_CONNECTED); + err = negotiate_mq(info); + if (err) + return err; + err = talk_to_blkback(dev, info); /* From 8a695db01dc2b07959628626bc3810c4c6ff2681 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Tue, 19 Jan 2016 08:57:48 -0700 Subject: [PATCH 016/489] dmaengine: IOATDMA: fix timer code that continues to restart channels during idle The timer_event() function seems to have a bug where it ends up marking the last entry as non-responding and eventually attempts to restart the channel. This also continuously happen when idle. What needs to happen is for us to make sure there are no descriptors active and then handle that case properly. We should only hit the "cleanup" stage if there are still active descriptors. Signed-off-by: Dave Jiang Signed-off-by: Vinod Koul --- drivers/dma/ioat/dma.c | 34 ++++++++++++++++++++++------------ 1 file changed, 22 insertions(+), 12 deletions(-) diff --git a/drivers/dma/ioat/dma.c b/drivers/dma/ioat/dma.c index 1d5df2ef148b..21539d5c54c3 100644 --- a/drivers/dma/ioat/dma.c +++ b/drivers/dma/ioat/dma.c @@ -861,32 +861,42 @@ void ioat_timer_event(unsigned long data) return; } + spin_lock_bh(&ioat_chan->cleanup_lock); + + /* handle the no-actives case */ + if (!ioat_ring_active(ioat_chan)) { + spin_lock_bh(&ioat_chan->prep_lock); + check_active(ioat_chan); + spin_unlock_bh(&ioat_chan->prep_lock); + spin_unlock_bh(&ioat_chan->cleanup_lock); + return; + } + /* if we haven't made progress and we have already * acknowledged a pending completion once, then be more * forceful with a restart */ - spin_lock_bh(&ioat_chan->cleanup_lock); if (ioat_cleanup_preamble(ioat_chan, &phys_complete)) __cleanup(ioat_chan, phys_complete); else if (test_bit(IOAT_COMPLETION_ACK, &ioat_chan->state)) { + u32 chanerr; + + chanerr = readl(ioat_chan->reg_base + IOAT_CHANERR_OFFSET); + dev_warn(to_dev(ioat_chan), "Restarting channel...\n"); + dev_warn(to_dev(ioat_chan), "CHANSTS: %#Lx CHANERR: %#x\n", + status, chanerr); + dev_warn(to_dev(ioat_chan), "Active descriptors: %d\n", + ioat_ring_active(ioat_chan)); + spin_lock_bh(&ioat_chan->prep_lock); ioat_restart_channel(ioat_chan); spin_unlock_bh(&ioat_chan->prep_lock); spin_unlock_bh(&ioat_chan->cleanup_lock); return; - } else { + } else set_bit(IOAT_COMPLETION_ACK, &ioat_chan->state); - mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT); - } - - if (ioat_ring_active(ioat_chan)) - mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT); - else { - spin_lock_bh(&ioat_chan->prep_lock); - check_active(ioat_chan); - spin_unlock_bh(&ioat_chan->prep_lock); - } + mod_timer(&ioat_chan->timer, jiffies + COMPLETION_TIMEOUT); spin_unlock_bh(&ioat_chan->cleanup_lock); } From 19f97c98307115f5a6b0bbf84850c9c272ce5dd3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 29 Jan 2016 22:32:49 +0530 Subject: [PATCH 017/489] powerpc/book3s_32: Fix build error with checkpoint restart MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In file included from mm/vmscan.c:54:0: include/linux/swapops.h: In function ‘pte_to_swp_entry’: include/linux/swapops.h:69:2: error: implicit declaration of function ‘pte_swp_soft_dirty’ [-Werror=implicit-function-declaration] if (pte_swp_soft_dirty(pte)) ^ include/linux/swapops.h:70:3: error: implicit declaration of function ‘pte_swp_clear_soft_dirty’ [-Werror=implicit-function-declaration] pte = pte_swp_clear_soft_dirty(pte); We support soft dirty tracking only with book3s 64 for now. So change the Kconfig dependency accordingly. Also CHECKPOINT_RESTORE feature is not really dependent on SOFT_DIRTY. We track the dependency between MEM_SOFT_DIRTY and ARCH_SOFT_DIRTY through headers Fixes: 7207f43665b8 ("powerpc/mm: Add page soft dirty tracking") Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 94f6c5089e0c..5ead6a31854b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -557,7 +557,7 @@ choice config PPC_4K_PAGES bool "4k page size" - select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S + select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64 config PPC_16K_PAGES bool "16k page size" @@ -566,7 +566,7 @@ config PPC_16K_PAGES config PPC_64K_PAGES bool "64k page size" depends on !PPC_FSL_BOOK3E && (44x || PPC_STD_MMU_64 || PPC_BOOK3E_64) - select HAVE_ARCH_SOFT_DIRTY if CHECKPOINT_RESTORE && PPC_BOOK3S + select HAVE_ARCH_SOFT_DIRTY if PPC_BOOK3S_64 config PPC_256K_PAGES bool "256k page size" From 7ddc971f86aa0a4cee9f6886c356a052461957ae Mon Sep 17 00:00:00 2001 From: Mike Krinkin Date: Sat, 30 Jan 2016 19:09:59 +0300 Subject: [PATCH 018/489] block: fix use-after-free in dio_bio_complete kasan reported the following error when i ran xfstest: [ 701.826854] ================================================================== [ 701.826864] BUG: KASAN: use-after-free in dio_bio_complete+0x41a/0x600 at addr ffff880080b95f94 [ 701.826870] Read of size 4 by task loop2/3874 [ 701.826879] page:ffffea000202e540 count:0 mapcount:0 mapping: (null) index:0x0 [ 701.826890] flags: 0x100000000000000() [ 701.826895] page dumped because: kasan: bad access detected [ 701.826904] CPU: 3 PID: 3874 Comm: loop2 Tainted: G B W L 4.5.0-rc1-next-20160129 #83 [ 701.826910] Hardware name: LENOVO 23205NG/23205NG, BIOS G2ET95WW (2.55 ) 07/09/2013 [ 701.826917] ffff88008fadf800 ffff88008fadf758 ffffffff81ca67bb 0000000041b58ab3 [ 701.826941] ffffffff830d1e74 ffffffff81ca6724 ffff88008fadf748 ffffffff8161c05c [ 701.826963] 0000000000000282 ffff88008fadf800 ffffed0010172bf2 ffffea000202e540 [ 701.826987] Call Trace: [ 701.826997] [] dump_stack+0x97/0xdc [ 701.827005] [] ? _atomic_dec_and_lock+0xc4/0xc4 [ 701.827014] [] ? __dump_page+0x32c/0x490 [ 701.827023] [] kasan_report_error+0x5f3/0x8b0 [ 701.827033] [] ? dio_bio_complete+0x41a/0x600 [ 701.827040] [] __asan_report_load4_noabort+0x59/0x80 [ 701.827048] [] ? dio_bio_complete+0x41a/0x600 [ 701.827053] [] dio_bio_complete+0x41a/0x600 [ 701.827057] [] ? blk_queue_exit+0x108/0x270 [ 701.827060] [] dio_bio_end_aio+0xa0/0x4d0 [ 701.827063] [] ? dio_bio_complete+0x600/0x600 [ 701.827067] [] ? blk_account_io_completion+0x316/0x5d0 [ 701.827070] [] bio_endio+0x79/0x200 [ 701.827074] [] blk_update_request+0x1df/0xc50 [ 701.827078] [] blk_mq_end_request+0x57/0x120 [ 701.827081] [] __blk_mq_complete_request+0x310/0x590 [ 701.827084] [] ? set_next_entity+0x2f8/0x2ed0 [ 701.827088] [] ? put_prev_entity+0x22d/0x2a70 [ 701.827091] [] blk_mq_complete_request+0x5b/0x80 [ 701.827094] [] loop_queue_work+0x273/0x19d0 [ 701.827098] [] ? finish_task_switch+0x1c8/0x8e0 [ 701.827101] [] ? trace_hardirqs_on_caller+0x18/0x6c0 [ 701.827104] [] ? lo_read_simple+0x890/0x890 [ 701.827108] [] ? debug_check_no_locks_freed+0x350/0x350 [ 701.827111] [] ? __hrtick_start+0x130/0x130 [ 701.827115] [] ? __schedule+0x936/0x20b0 [ 701.827118] [] ? kthread_worker_fn+0x3ed/0x8d0 [ 701.827121] [] ? kthread_worker_fn+0x21d/0x8d0 [ 701.827125] [] ? trace_hardirqs_on_caller+0x18/0x6c0 [ 701.827128] [] kthread_worker_fn+0x2af/0x8d0 [ 701.827132] [] ? __init_kthread_worker+0x170/0x170 [ 701.827135] [] ? _raw_spin_unlock_irqrestore+0x36/0x60 [ 701.827138] [] ? __init_kthread_worker+0x170/0x170 [ 701.827141] [] ? __init_kthread_worker+0x170/0x170 [ 701.827144] [] kthread+0x24b/0x3a0 [ 701.827148] [] ? kthread_create_on_node+0x4c0/0x4c0 [ 701.827151] [] ? trace_hardirqs_on+0xd/0x10 [ 701.827155] [] ? do_group_exit+0xdd/0x350 [ 701.827158] [] ? kthread_create_on_node+0x4c0/0x4c0 [ 701.827161] [] ret_from_fork+0x3f/0x70 [ 701.827165] [] ? kthread_create_on_node+0x4c0/0x4c0 [ 701.827167] Memory state around the buggy address: [ 701.827170] ffff880080b95e80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 701.827172] ffff880080b95f00: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 701.827175] >ffff880080b95f80: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 701.827177] ^ [ 701.827179] ffff880080b96000: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 701.827182] ffff880080b96080: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff [ 701.827183] ================================================================== The problem is that bio_check_pages_dirty calls bio_put, so we must not access bio fields after bio_check_pages_dirty. Fixes: 9b81c842355ac96097ba ("block: don't access bio->bi_error after bio_put()"). Signed-off-by: Mike Krinkin Cc: stable@vger.kernel.org Signed-off-by: Jens Axboe --- fs/direct-io.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/direct-io.c b/fs/direct-io.c index 1b2f7ffc8b84..d6a9012d42ad 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -472,8 +472,8 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio) dio->io_error = -EIO; if (dio->is_async && dio->rw == READ && dio->should_dirty) { - bio_check_pages_dirty(bio); /* transfers ownership */ err = bio->bi_error; + bio_check_pages_dirty(bio); /* transfers ownership */ } else { bio_for_each_segment_all(bvec, bio, i) { struct page *page = bvec->bv_page; From 7e502e5bc546a8d8be188fa019fe6fcdf02e3c87 Mon Sep 17 00:00:00 2001 From: Oren Givon Date: Mon, 25 Jan 2016 12:00:42 +0200 Subject: [PATCH 019/489] iwlwifi: fix name of ucode loaded for 8265 series Fix the name of the ucode being loaded for 8265 series to be: iwlwifi-8265-XX.ucode Signed-off-by: Oren Givon Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/intel/iwlwifi/iwl-8000.c | 42 +++++++++++++++---- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 6 ++- 2 files changed, 37 insertions(+), 11 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c index c84a0299d43e..bce9b3420a13 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-8000.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-8000.c @@ -7,6 +7,7 @@ * * Copyright(c) 2014 Intel Corporation. All rights reserved. * Copyright(c) 2014 - 2015 Intel Mobile Communications GmbH + * Copyright(c) 2016 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of version 2 of the GNU General Public License as @@ -70,12 +71,15 @@ /* Highest firmware API version supported */ #define IWL8000_UCODE_API_MAX 20 +#define IWL8265_UCODE_API_MAX 20 /* Oldest version we won't warn about */ #define IWL8000_UCODE_API_OK 13 +#define IWL8265_UCODE_API_OK 20 /* Lowest firmware API version supported */ #define IWL8000_UCODE_API_MIN 13 +#define IWL8265_UCODE_API_MIN 20 /* NVM versions */ #define IWL8000_NVM_VERSION 0x0a1d @@ -93,6 +97,10 @@ #define IWL8000_MODULE_FIRMWARE(api) \ IWL8000_FW_PRE "-" __stringify(api) ".ucode" +#define IWL8265_FW_PRE "iwlwifi-8265-" +#define IWL8265_MODULE_FIRMWARE(api) \ + IWL8265_FW_PRE __stringify(api) ".ucode" + #define NVM_HW_SECTION_NUM_FAMILY_8000 10 #define DEFAULT_NVM_FILE_FAMILY_8000B "nvmData-8000B" #define DEFAULT_NVM_FILE_FAMILY_8000C "nvmData-8000C" @@ -144,10 +152,7 @@ static const struct iwl_tt_params iwl8000_tt_params = { .support_tx_backoff = true, }; -#define IWL_DEVICE_8000 \ - .ucode_api_max = IWL8000_UCODE_API_MAX, \ - .ucode_api_ok = IWL8000_UCODE_API_OK, \ - .ucode_api_min = IWL8000_UCODE_API_MIN, \ +#define IWL_DEVICE_8000_COMMON \ .device_family = IWL_DEVICE_FAMILY_8000, \ .max_inst_size = IWL60_RTC_INST_SIZE, \ .max_data_size = IWL60_RTC_DATA_SIZE, \ @@ -167,10 +172,28 @@ static const struct iwl_tt_params iwl8000_tt_params = { .thermal_params = &iwl8000_tt_params, \ .apmg_not_supported = true +#define IWL_DEVICE_8000 \ + IWL_DEVICE_8000_COMMON, \ + .ucode_api_max = IWL8000_UCODE_API_MAX, \ + .ucode_api_ok = IWL8000_UCODE_API_OK, \ + .ucode_api_min = IWL8000_UCODE_API_MIN \ + +#define IWL_DEVICE_8260 \ + IWL_DEVICE_8000_COMMON, \ + .ucode_api_max = IWL8000_UCODE_API_MAX, \ + .ucode_api_ok = IWL8000_UCODE_API_OK, \ + .ucode_api_min = IWL8000_UCODE_API_MIN \ + +#define IWL_DEVICE_8265 \ + IWL_DEVICE_8000_COMMON, \ + .ucode_api_max = IWL8265_UCODE_API_MAX, \ + .ucode_api_ok = IWL8265_UCODE_API_OK, \ + .ucode_api_min = IWL8265_UCODE_API_MIN \ + const struct iwl_cfg iwl8260_2n_cfg = { .name = "Intel(R) Dual Band Wireless N 8260", .fw_name_pre = IWL8000_FW_PRE, - IWL_DEVICE_8000, + IWL_DEVICE_8260, .ht_params = &iwl8000_ht_params, .nvm_ver = IWL8000_NVM_VERSION, .nvm_calib_ver = IWL8000_TX_POWER_VERSION, @@ -179,7 +202,7 @@ const struct iwl_cfg iwl8260_2n_cfg = { const struct iwl_cfg iwl8260_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 8260", .fw_name_pre = IWL8000_FW_PRE, - IWL_DEVICE_8000, + IWL_DEVICE_8260, .ht_params = &iwl8000_ht_params, .nvm_ver = IWL8000_NVM_VERSION, .nvm_calib_ver = IWL8000_TX_POWER_VERSION, @@ -188,8 +211,8 @@ const struct iwl_cfg iwl8260_2ac_cfg = { const struct iwl_cfg iwl8265_2ac_cfg = { .name = "Intel(R) Dual Band Wireless AC 8265", - .fw_name_pre = IWL8000_FW_PRE, - IWL_DEVICE_8000, + .fw_name_pre = IWL8265_FW_PRE, + IWL_DEVICE_8265, .ht_params = &iwl8000_ht_params, .nvm_ver = IWL8000_NVM_VERSION, .nvm_calib_ver = IWL8000_TX_POWER_VERSION, @@ -209,7 +232,7 @@ const struct iwl_cfg iwl4165_2ac_cfg = { const struct iwl_cfg iwl8260_2ac_sdio_cfg = { .name = "Intel(R) Dual Band Wireless-AC 8260", .fw_name_pre = IWL8000_FW_PRE, - IWL_DEVICE_8000, + IWL_DEVICE_8260, .ht_params = &iwl8000_ht_params, .nvm_ver = IWL8000_NVM_VERSION, .nvm_calib_ver = IWL8000_TX_POWER_VERSION, @@ -236,3 +259,4 @@ const struct iwl_cfg iwl4165_2ac_sdio_cfg = { }; MODULE_FIRMWARE(IWL8000_MODULE_FIRMWARE(IWL8000_UCODE_API_OK)); +MODULE_FIRMWARE(IWL8265_MODULE_FIRMWARE(IWL8265_UCODE_API_OK)); diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 7acb49075683..ab4c2a0470b2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -243,8 +243,10 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) if (drv->trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) { char rev_step = 'A' + CSR_HW_REV_STEP(drv->trans->hw_rev); - snprintf(drv->firmware_name, sizeof(drv->firmware_name), - "%s%c-%s.ucode", name_pre, rev_step, tag); + if (rev_step != 'A') + snprintf(drv->firmware_name, + sizeof(drv->firmware_name), "%s%c-%s.ucode", + name_pre, rev_step, tag); } IWL_DEBUG_INFO(drv, "attempting to load firmware %s'%s'\n", From d93c6258ee4255749c10012c50a31c08f4e9fb16 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 20 Jan 2016 11:16:43 +0100 Subject: [PATCH 020/489] netfilter: conntrack: resched in nf_ct_iterate_cleanup Ulrich reports soft lockup with following (shortened) callchain: NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! __netif_receive_skb_core+0x6e4/0x774 process_backlog+0x94/0x160 net_rx_action+0x88/0x178 call_do_softirq+0x24/0x3c do_softirq+0x54/0x6c __local_bh_enable_ip+0x7c/0xbc nf_ct_iterate_cleanup+0x11c/0x22c [nf_conntrack] masq_inet_event+0x20/0x30 [nf_nat_masquerade_ipv6] atomic_notifier_call_chain+0x1c/0x2c ipv6_del_addr+0x1bc/0x220 [ipv6] Problem is that nf_ct_iterate_cleanup can run for a very long time since it can be interrupted by softirq processing. Moreover, atomic_notifier_call_chain runs with rcu readlock held. So lets call cond_resched() in nf_ct_iterate_cleanup and defer the call to a work queue for the atomic_notifier_call_chain case. We also need another cond_resched in get_next_corpse, since we have to deal with iter() always returning false, in that case get_next_corpse will walk entire conntrack table. Reported-by: Ulrich Weber Tested-by: Ulrich Weber Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_nat_masquerade_ipv6.c | 74 ++++++++++++++++++++- net/netfilter/nf_conntrack_core.c | 5 ++ 2 files changed, 76 insertions(+), 3 deletions(-) diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 31ba7ca19757..051b6a6bfff6 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -21,6 +21,10 @@ #include #include +#define MAX_WORK_COUNT 16 + +static atomic_t v6_worker_count; + unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, const struct net_device *out) @@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; +struct masq_dev_work { + struct work_struct work; + struct net *net; + int ifindex; +}; + +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + long index; + + w = container_of(work, struct masq_dev_work, work); + + index = w->ifindex; + nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&v6_worker_count); + module_put(THIS_MODULE); +} + +/* ipv6 inet notifier is an atomic notifier, i.e. we cannot + * schedule. + * + * Unfortunately, nf_ct_iterate_cleanup can run for a long + * time if there are lots of conntracks and the system + * handles high softirq load, so it frequently calls cond_resched + * while iterating the conntrack table. + * + * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * + * As we can have 'a lot' of inet_events (depending on amount + * of ipv6 addresses being deleted), we also need to add an upper + * limit to the number of queued work items. + */ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; - struct netdev_notifier_info info; + const struct net_device *dev; + struct masq_dev_work *w; + struct net *net; - netdev_notifier_info_init(&info, ifa->idev->dev); - return masq_device_event(this, event, &info); + if (event != NETDEV_DOWN || + atomic_read(&v6_worker_count) >= MAX_WORK_COUNT) + return NOTIFY_DONE; + + dev = ifa->idev->dev; + net = maybe_get_net(dev_net(dev)); + if (!net) + return NOTIFY_DONE; + + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + atomic_inc(&v6_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = dev->ifindex; + w->net = net; + schedule_work(&w->work); + + return NOTIFY_DONE; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); + return NOTIFY_DONE; } static struct notifier_block masq_inet_notifier = { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 58882de06bd7..f60b4fdeeb8c 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1412,6 +1412,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), } spin_unlock(lockp); local_bh_enable(); + cond_resched(); } for_each_possible_cpu(cpu) { @@ -1424,6 +1425,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data), set_bit(IPS_DYING_BIT, &ct->status); } spin_unlock_bh(&pcpu->lock); + cond_resched(); } return NULL; found: @@ -1440,6 +1442,8 @@ void nf_ct_iterate_cleanup(struct net *net, struct nf_conn *ct; unsigned int bucket = 0; + might_sleep(); + while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) { /* Time to push up daises... */ if (del_timer(&ct->timeout)) @@ -1448,6 +1452,7 @@ void nf_ct_iterate_cleanup(struct net *net, /* ... else the timer will get him soon. */ nf_ct_put(ct); + cond_resched(); } } EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup); From 7c7bdf35991bb8f7cfaeaf22ea3a2f2d1967c166 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 24 Jan 2016 23:08:39 +0100 Subject: [PATCH 021/489] netfilter: nfnetlink: use original skbuff when acking batches Since bd678e09dc17 ("netfilter: nfnetlink: fix splat due to incorrect socket memory accounting in skbuff clones"), we don't manually attach the sk to the skbuff clone anymore, so we have to use the original skbuff from netlink_ack() which needs to access the sk pointer. Fixes: bd678e09dc17 ("netfilter: nfnetlink: fix splat due to incorrect socket memory accounting in skbuff clones") Reported-by: Dmitry Vyukov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index a7ba23353dab..62e92af2384a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -311,14 +311,14 @@ replay: #endif { nfnl_unlock(subsys_id); - netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(oskb, nlh, -EOPNOTSUPP); return kfree_skb(skb); } } if (!ss->commit || !ss->abort) { nfnl_unlock(subsys_id); - netlink_ack(skb, nlh, -EOPNOTSUPP); + netlink_ack(oskb, nlh, -EOPNOTSUPP); return kfree_skb(skb); } @@ -406,7 +406,7 @@ ack: * pointing to the batch header. */ nfnl_err_reset(&err_list); - netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM); + netlink_ack(oskb, nlmsg_hdr(oskb), -ENOMEM); status |= NFNL_BATCH_FAILURE; goto done; } From 53c520c2ab79e9f3765d24116ab54f6d5b3cd563 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 28 Jan 2016 13:16:59 +0100 Subject: [PATCH 022/489] netfilter: cttimeout: fix deadlock due to erroneous unlock/lock conversion The spin_unlock call should have been left as-is, revert. Fixes: b16c29191dc89bd ("netfilter: nf_conntrack: use safer way to lock all buckets") Reported-by: kernel test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink_cttimeout.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 94837d236ab0..2671b9deb103 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -312,7 +312,7 @@ static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout) hlist_nulls_for_each_entry(h, nn, &net->ct.hash[i], hnnode) untimeout(h, timeout); } - nf_conntrack_lock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); + spin_unlock(&nf_conntrack_locks[i % CONNTRACK_LOCKS]); } local_bh_enable(); } From a0c80efe5956ccce9fe7ae5c78542578c07bc20a Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Mon, 1 Feb 2016 11:19:17 +0100 Subject: [PATCH 023/489] floppy: fix lock_fdc() signal handling floppy_revalidate() doesn't perform any error handling on lock_fdc() result. lock_fdc() might actually be interrupted by a signal (it waits for fdc becoming non-busy interruptibly). In such case, floppy_revalidate() proceeds as if it had claimed the lock, but it fact it doesn't. In case of multiple threads trying to open("/dev/fdX"), this leads to serious corruptions all over the place, because all of a sudden there is no critical section protection (that'd otherwise be guaranteed by locked fd) whatsoever. While at this, fix the fact that the 'interruptible' parameter to lock_fdc() doesn't make any sense whatsoever, because we always wait interruptibly anyway. Most of the lock_fdc() callsites do properly handle error (and propagate EINTR), but floppy_revalidate() and floppy_check_events() don't. Fix this. Spotted by 'syzkaller' tool. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Jiri Kosina --- drivers/block/floppy.c | 33 ++++++++++++++++++--------------- 1 file changed, 18 insertions(+), 15 deletions(-) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index fa9bb742df6e..c1aacca88c8f 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -866,7 +866,7 @@ static void set_fdc(int drive) } /* locks the driver */ -static int lock_fdc(int drive, bool interruptible) +static int lock_fdc(int drive) { if (WARN(atomic_read(&usage_count) == 0, "Trying to lock fdc while usage count=0\n")) @@ -2173,7 +2173,7 @@ static int do_format(int drive, struct format_descr *tmp_format_req) { int ret; - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; set_floppy(drive); @@ -2960,7 +2960,7 @@ static int user_reset_fdc(int drive, int arg, bool interruptible) { int ret; - if (lock_fdc(drive, interruptible)) + if (lock_fdc(drive)) return -EINTR; if (arg == FD_RESET_ALWAYS) @@ -3243,7 +3243,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, if (!capable(CAP_SYS_ADMIN)) return -EPERM; mutex_lock(&open_lock); - if (lock_fdc(drive, true)) { + if (lock_fdc(drive)) { mutex_unlock(&open_lock); return -EINTR; } @@ -3263,7 +3263,7 @@ static int set_geometry(unsigned int cmd, struct floppy_struct *g, } else { int oldStretch; - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; if (cmd != FDDEFPRM) { /* notice a disk change immediately, else @@ -3349,7 +3349,7 @@ static int get_floppy_geometry(int drive, int type, struct floppy_struct **g) if (type) *g = &floppy_type[type]; else { - if (lock_fdc(drive, false)) + if (lock_fdc(drive)) return -EINTR; if (poll_drive(false, 0) == -EINTR) return -EINTR; @@ -3433,7 +3433,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int if (UDRS->fd_ref != 1) /* somebody else has this drive open */ return -EBUSY; - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; /* do the actual eject. Fails on @@ -3445,7 +3445,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int process_fd_request(); return ret; case FDCLRPRM: - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; current_type[drive] = NULL; floppy_sizes[drive] = MAX_DISK_SIZE << 1; @@ -3467,7 +3467,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int UDP->flags &= ~FTD_MSG; return 0; case FDFMTBEG: - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR) return -EINTR; @@ -3484,7 +3484,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int return do_format(drive, &inparam.f); case FDFMTEND: case FDFLUSH: - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; return invalidate_drive(bdev); case FDSETEMSGTRESH: @@ -3507,7 +3507,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int outparam = UDP; break; case FDPOLLDRVSTAT: - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; if (poll_drive(true, FD_RAW_NEED_DISK) == -EINTR) return -EINTR; @@ -3530,7 +3530,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int case FDRAWCMD: if (type) return -EINVAL; - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; set_floppy(drive); i = raw_cmd_ioctl(cmd, (void __user *)param); @@ -3539,7 +3539,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int process_fd_request(); return i; case FDTWADDLE: - if (lock_fdc(drive, true)) + if (lock_fdc(drive)) return -EINTR; twaddle(); process_fd_request(); @@ -3747,7 +3747,8 @@ static unsigned int floppy_check_events(struct gendisk *disk, return DISK_EVENT_MEDIA_CHANGE; if (time_after(jiffies, UDRS->last_checked + UDP->checkfreq)) { - lock_fdc(drive, false); + if (lock_fdc(drive)) + return -EINTR; poll_drive(false, 0); process_fd_request(); } @@ -3845,7 +3846,9 @@ static int floppy_revalidate(struct gendisk *disk) "VFS: revalidate called on non-open device.\n")) return -EFAULT; - lock_fdc(drive, false); + res = lock_fdc(drive); + if (res) + return res; cf = (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags) || test_bit(FD_VERIFY_BIT, &UDRS->flags)); if (!(cf || test_bit(drive, &fake_change) || drive_no_geom(drive))) { From e502fb8f8801c9561c57397e7fd917187762324e Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Thu, 14 Jan 2016 14:41:32 -0800 Subject: [PATCH 024/489] deadline: remove unused struct member commit 63de428b139d3d31d86ebe25ae97b33f6540fb7e ("deadline-iosched: allow non-sequential batching") removed last use of last_sector. Signed-off-by: Tahsin Erdogan Reviewed-by: Jeff Moyer Signed-off-by: Jens Axboe --- block/deadline-iosched.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/block/deadline-iosched.c b/block/deadline-iosched.c index a753df2b3fc2..d0dd7882d8c7 100644 --- a/block/deadline-iosched.c +++ b/block/deadline-iosched.c @@ -39,7 +39,6 @@ struct deadline_data { */ struct request *next_rq[2]; unsigned int batching; /* number of sequential requests made */ - sector_t last_sector; /* head position */ unsigned int starved; /* times reads have starved writes */ /* @@ -210,8 +209,6 @@ deadline_move_request(struct deadline_data *dd, struct request *rq) dd->next_rq[WRITE] = NULL; dd->next_rq[data_dir] = deadline_latter_request(rq); - dd->last_sector = rq_end_sector(rq); - /* * take it off the sort and fifo list, move * to dispatch queue From 474f2ba268f220e75ed7b9bfa7b977ade740d30c Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Thu, 14 Jan 2016 14:24:32 -0500 Subject: [PATCH 025/489] clk: tegra: Fix naming of MISC registers Some register for PLLM and PLLMB were named MISC0 but according to the TRM, they have different names. Sync up the names to make it easier to understand which register they are really referring to. Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 36 ++++++++++++++++---------------- 1 file changed, 18 insertions(+), 18 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index f45c9adf7fb2..caae0dcc9cb5 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -59,8 +59,8 @@ #define PLLC3_MISC3 0x50c #define PLLM_BASE 0x90 -#define PLLM_MISC0 0x9c #define PLLM_MISC1 0x98 +#define PLLM_MISC2 0x9c #define PLLP_BASE 0xa0 #define PLLP_MISC0 0xac #define PLLP_MISC1 0x680 @@ -99,7 +99,7 @@ #define PLLC4_MISC0 0x5a8 #define PLLC4_OUT 0x5e4 #define PLLMB_BASE 0x5e8 -#define PLLMB_MISC0 0x5ec +#define PLLMB_MISC1 0x5ec #define PLLA1_BASE 0x6a4 #define PLLA1_MISC0 0x6a8 #define PLLA1_MISC1 0x6ac @@ -367,12 +367,12 @@ static const char *mux_pllmcp_clkm[] = { /* PLLMB */ #define PLLMB_BASE_LOCK (1 << 27) -#define PLLMB_MISC0_LOCK_OVERRIDE (1 << 18) -#define PLLMB_MISC0_IDDQ (1 << 17) -#define PLLMB_MISC0_LOCK_ENABLE (1 << 16) +#define PLLMB_MISC1_LOCK_OVERRIDE (1 << 18) +#define PLLMB_MISC1_IDDQ (1 << 17) +#define PLLMB_MISC1_LOCK_ENABLE (1 << 16) -#define PLLMB_MISC0_DEFAULT_VALUE 0x00030000 -#define PLLMB_MISC0_WRITE_MASK 0x0007ffff +#define PLLMB_MISC1_DEFAULT_VALUE 0x00030000 +#define PLLMB_MISC1_WRITE_MASK 0x0007ffff /* PLLP */ #define PLLP_BASE_OVERRIDE (1 << 28) @@ -914,15 +914,15 @@ void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb) * PLL is ON: check if defaults already set, then set those * that can be updated in flight. */ - val = PLLMB_MISC0_DEFAULT_VALUE & (~PLLMB_MISC0_IDDQ); - mask = PLLMB_MISC0_LOCK_ENABLE | PLLMB_MISC0_LOCK_OVERRIDE; + val = PLLMB_MISC1_DEFAULT_VALUE & (~PLLMB_MISC1_IDDQ); + mask = PLLMB_MISC1_LOCK_ENABLE | PLLMB_MISC1_LOCK_OVERRIDE; _pll_misc_chk_default(clk_base, pllmb->params, 0, val, - ~mask & PLLMB_MISC0_WRITE_MASK); + ~mask & PLLMB_MISC1_WRITE_MASK); /* Enable lock detect */ val = readl_relaxed(clk_base + pllmb->params->ext_misc_reg[0]); val &= ~mask; - val |= PLLMB_MISC0_DEFAULT_VALUE & mask; + val |= PLLMB_MISC1_DEFAULT_VALUE & mask; writel_relaxed(val, clk_base + pllmb->params->ext_misc_reg[0]); udelay(1); @@ -930,7 +930,7 @@ void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb) } /* set IDDQ, enable lock detect */ - writel_relaxed(PLLMB_MISC0_DEFAULT_VALUE, + writel_relaxed(PLLMB_MISC1_DEFAULT_VALUE, clk_base + pllmb->params->ext_misc_reg[0]); udelay(1); } @@ -1557,14 +1557,14 @@ static struct tegra_clk_pll_params pll_m_params = { .vco_min = 800000000, .vco_max = 1866000000, .base_reg = PLLM_BASE, - .misc_reg = PLLM_MISC0, + .misc_reg = PLLM_MISC2, .lock_mask = PLL_BASE_LOCK, .lock_enable_bit_idx = PLLM_MISC_LOCK_ENABLE, .lock_delay = 300, - .iddq_reg = PLLM_MISC0, + .iddq_reg = PLLM_MISC2, .iddq_bit_idx = PLLM_IDDQ_BIT, .max_p = PLL_QLIN_PDIV_MAX, - .ext_misc_reg[0] = PLLM_MISC0, + .ext_misc_reg[0] = PLLM_MISC2, .ext_misc_reg[0] = PLLM_MISC1, .round_p_to_pdiv = pll_qlin_p_to_pdiv, .pdiv_tohw = pll_qlin_pdiv_to_hw, @@ -1584,13 +1584,13 @@ static struct tegra_clk_pll_params pll_mb_params = { .vco_min = 800000000, .vco_max = 1866000000, .base_reg = PLLMB_BASE, - .misc_reg = PLLMB_MISC0, + .misc_reg = PLLMB_MISC1, .lock_mask = PLL_BASE_LOCK, .lock_delay = 300, - .iddq_reg = PLLMB_MISC0, + .iddq_reg = PLLMB_MISC1, .iddq_bit_idx = PLLMB_IDDQ_BIT, .max_p = PLL_QLIN_PDIV_MAX, - .ext_misc_reg[0] = PLLMB_MISC0, + .ext_misc_reg[0] = PLLMB_MISC1, .round_p_to_pdiv = pll_qlin_p_to_pdiv, .pdiv_tohw = pll_qlin_pdiv_to_hw, .div_nmp = &pllm_nmp, From 736971bed20de137db9b418cc641c7d11336fffb Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Thu, 14 Jan 2016 14:24:33 -0500 Subject: [PATCH 026/489] clk: tegra: Fix the misnaming of nvenc from msenc When adding the nvenc clock, it was partially named msenc in the code. Since the msenc clock isn't present in Tegra210 and has been replaced by the nvenc clock, its misleading to see it present. Therefore, properly rename it. Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra-periph.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c index 105405ca85ab..1860df1862dd 100644 --- a/drivers/clk/tegra/clk-tegra-periph.c +++ b/drivers/clk/tegra/clk-tegra-periph.c @@ -773,7 +773,7 @@ static struct tegra_periph_init_data periph_clks[] = { XUSB("xusb_dev_src", mux_clkm_pllp_pllc_pllre, CLK_SOURCE_XUSB_DEV_SRC, 95, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_dev_src), XUSB("xusb_dev_src", mux_clkm_pllp_pllre, CLK_SOURCE_XUSB_DEV_SRC, 95, TEGRA_PERIPH_ON_APB | TEGRA_PERIPH_NO_RESET, tegra_clk_xusb_dev_src_8), MUX8("dbgapb", mux_pllp_clkm_2, CLK_SOURCE_DBGAPB, 185, TEGRA_PERIPH_NO_RESET, tegra_clk_dbgapb), - MUX8("msenc", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVENC, 219, 0, tegra_clk_nvenc), + MUX8("nvenc", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVENC, 219, 0, tegra_clk_nvenc), MUX8("nvdec", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVDEC, 194, 0, tegra_clk_nvdec), MUX8("nvjpg", mux_pllc2_c_c3_pllp_plla1_clkm, CLK_SOURCE_NVJPG, 195, 0, tegra_clk_nvjpg), MUX8("ape", mux_plla_pllc4_out0_pllc_pllc4_out1_pllp_pllc4_out2_clkm, CLK_SOURCE_APE, 198, TEGRA_PERIPH_ON_APB, tegra_clk_ape), From 3eb61566a6efc5a56ebe1e6b86519bc5e0b39003 Mon Sep 17 00:00:00 2001 From: Andrew Bresticker Date: Thu, 14 Jan 2016 14:24:34 -0500 Subject: [PATCH 027/489] clk: tegra: pll: Fix potential sleeping-while-atomic Since the ->enable() callback is called with a spinlock held, we cannot call potentially blocking functions such as clk_get_rate() or clk_get_parent(), so use the unlocked versions instead. Signed-off-by: Andrew Bresticker [rklein: Adapted from ChromeOS patch, removing pllu_enable cleanup as it isn't present upstream] Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-pll.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c index a534bfab30b3..65156486889a 100644 --- a/drivers/clk/tegra/clk-pll.c +++ b/drivers/clk/tegra/clk-pll.c @@ -880,7 +880,7 @@ static int clk_plle_training(struct tegra_clk_pll *pll) static int clk_plle_enable(struct clk_hw *hw) { struct tegra_clk_pll *pll = to_clk_pll(hw); - unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk)); + unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw)); struct tegra_clk_pll_freq_table sel; u32 val; int err; @@ -1378,7 +1378,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw) u32 val; int ret; unsigned long flags = 0; - unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk)); + unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw)); if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate)) return -EINVAL; @@ -2014,7 +2014,7 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw) u32 val; int ret; unsigned long flags = 0; - unsigned long input_rate = clk_get_rate(clk_get_parent(hw->clk)); + unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw)); if (_get_table_rate(hw, &sel, pll->params->fixed_rate, input_rate)) return -EINVAL; From 3dad5c5fa1d24c3bbb3e9e8ac0c52f35e045b807 Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Thu, 14 Jan 2016 14:24:35 -0500 Subject: [PATCH 028/489] clk: tegra: Fix pllx dyn step calculation The logic for calculating the input rate used when figuring out the proper dynamic steps for pllx was incorrect. It is supposed to be calculated using parent_rate / m but it was just using the parent rate directly, therefore using the wrong step values. Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index caae0dcc9cb5..ffcb86a667d9 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -780,13 +780,13 @@ static void pllx_get_dyn_steps(struct clk_hw *hw, u32 *step_a, u32 *step_b) { unsigned long input_rate; - if (!IS_ERR_OR_NULL(hw->clk)) { + /* cf rate */ + if (!IS_ERR_OR_NULL(hw->clk)) input_rate = clk_hw_get_rate(clk_hw_get_parent(hw)); - /* cf rate */ - input_rate /= tegra_pll_get_fixed_mdiv(hw, input_rate); - } else { + else input_rate = 38400000; - } + + input_rate /= tegra_pll_get_fixed_mdiv(hw, input_rate); switch (input_rate) { case 12000000: From f59b0168d3f3257f9bf0734563290acc3c9d972b Mon Sep 17 00:00:00 2001 From: Mark Kuo Date: Thu, 14 Jan 2016 14:24:36 -0500 Subject: [PATCH 029/489] clk: tegra: Do not disable PLLE when under hardware control Software should not disable PLLE if PLLE is already put under hardware control. Signed-off-by: Mark Kuo Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-pll.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c index 65156486889a..d9c3109b75bd 100644 --- a/drivers/clk/tegra/clk-pll.c +++ b/drivers/clk/tegra/clk-pll.c @@ -2012,7 +2012,7 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw) struct tegra_clk_pll *pll = to_clk_pll(hw); struct tegra_clk_pll_freq_table sel; u32 val; - int ret; + int ret = 0; unsigned long flags = 0; unsigned long input_rate = clk_hw_get_rate(clk_hw_get_parent(hw)); @@ -2022,16 +2022,14 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw) if (pll->lock) spin_lock_irqsave(pll->lock, flags); + val = pll_readl(pll->params->aux_reg, pll); + if (val & PLLE_AUX_SEQ_ENABLE) + goto out; + val = pll_readl_base(pll); val &= ~BIT(30); /* Disable lock override */ pll_writel_base(val, pll); - val = pll_readl(pll->params->aux_reg, pll); - val |= PLLE_AUX_ENABLE_SWCTL; - val &= ~PLLE_AUX_SEQ_ENABLE; - pll_writel(val, pll->params->aux_reg, pll); - udelay(1); - val = pll_readl_misc(pll); val |= PLLE_MISC_LOCK_ENABLE; val |= PLLE_MISC_IDDQ_SW_CTRL; @@ -2104,15 +2102,25 @@ static void clk_plle_tegra210_disable(struct clk_hw *hw) if (pll->lock) spin_lock_irqsave(pll->lock, flags); + /* If PLLE HW sequencer is enabled, SW should not disable PLLE */ + val = pll_readl(pll->params->aux_reg, pll); + if (val & PLLE_AUX_SEQ_ENABLE) + goto out; + val = pll_readl_base(pll); val &= ~PLLE_BASE_ENABLE; pll_writel_base(val, pll); + val = pll_readl(pll->params->aux_reg, pll); + val |= PLLE_AUX_ENABLE_SWCTL | PLLE_AUX_SS_SWCTL; + pll_writel(val, pll->params->aux_reg, pll); + val = pll_readl_misc(pll); val |= PLLE_MISC_IDDQ_SW_CTRL | PLLE_MISC_IDDQ_SW_VALUE; pll_writel_misc(val, pll); udelay(1); +out: if (pll->lock) spin_unlock_irqrestore(pll->lock, flags); } From fd2963b071c1346572285a274a6ae8f26a970c4d Mon Sep 17 00:00:00 2001 From: Rhyland Klein Date: Thu, 14 Jan 2016 14:24:37 -0500 Subject: [PATCH 030/489] clk: tegra: Fix typos around clearing PLLE bits during enable While enabling PLLE on both Tegra114 and Tegra210, we should be clearing PLLE_MISC_VREG_BG_CTRL_MASK and PLLE_MISC_VREG_CTRL_MASK not setting them. This patch fixes both places where we incorrectly set instead of cleared those bits. Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-pll.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c index d9c3109b75bd..cb28130e6c0a 100644 --- a/drivers/clk/tegra/clk-pll.c +++ b/drivers/clk/tegra/clk-pll.c @@ -1401,7 +1401,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw) val |= PLLE_MISC_IDDQ_SW_CTRL; val &= ~PLLE_MISC_IDDQ_SW_VALUE; val |= PLLE_MISC_PLLE_PTS; - val |= PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK; + val &= ~(PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK); pll_writel_misc(val, pll); udelay(5); @@ -2035,7 +2035,7 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw) val |= PLLE_MISC_IDDQ_SW_CTRL; val &= ~PLLE_MISC_IDDQ_SW_VALUE; val |= PLLE_MISC_PLLE_PTS; - val |= PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK; + val &= ~(PLLE_MISC_VREG_BG_CTRL_MASK | PLLE_MISC_VREG_CTRL_MASK); pll_writel_misc(val, pll); udelay(5); From 442f53fb1be44c00263ebb8e7c2eff19dd019037 Mon Sep 17 00:00:00 2001 From: Mark Kuo Date: Thu, 14 Jan 2016 14:26:42 -0500 Subject: [PATCH 031/489] clk: tegra: Fix PLLE SS coefficients The PLLE SS coefficients are different between Tegra210 and Tegra114. Add SoC generation specific versions for Tegra114 and Tegra210 and use them in their respective ->enable() callbacks. Signed-off-by: Mark Kuo Signed-off-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-pll.c | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) diff --git a/drivers/clk/tegra/clk-pll.c b/drivers/clk/tegra/clk-pll.c index cb28130e6c0a..6ac3f843e7ca 100644 --- a/drivers/clk/tegra/clk-pll.c +++ b/drivers/clk/tegra/clk-pll.c @@ -86,15 +86,21 @@ #define PLLE_SS_DISABLE (PLLE_SS_CNTL_BYPASS_SS | PLLE_SS_CNTL_INTERP_RESET |\ PLLE_SS_CNTL_SSC_BYP) #define PLLE_SS_MAX_MASK 0x1ff -#define PLLE_SS_MAX_VAL 0x25 +#define PLLE_SS_MAX_VAL_TEGRA114 0x25 +#define PLLE_SS_MAX_VAL_TEGRA210 0x21 #define PLLE_SS_INC_MASK (0xff << 16) #define PLLE_SS_INC_VAL (0x1 << 16) #define PLLE_SS_INCINTRV_MASK (0x3f << 24) -#define PLLE_SS_INCINTRV_VAL (0x20 << 24) +#define PLLE_SS_INCINTRV_VAL_TEGRA114 (0x20 << 24) +#define PLLE_SS_INCINTRV_VAL_TEGRA210 (0x23 << 24) #define PLLE_SS_COEFFICIENTS_MASK \ (PLLE_SS_MAX_MASK | PLLE_SS_INC_MASK | PLLE_SS_INCINTRV_MASK) -#define PLLE_SS_COEFFICIENTS_VAL \ - (PLLE_SS_MAX_VAL | PLLE_SS_INC_VAL | PLLE_SS_INCINTRV_VAL) +#define PLLE_SS_COEFFICIENTS_VAL_TEGRA114 \ + (PLLE_SS_MAX_VAL_TEGRA114 | PLLE_SS_INC_VAL |\ + PLLE_SS_INCINTRV_VAL_TEGRA114) +#define PLLE_SS_COEFFICIENTS_VAL_TEGRA210 \ + (PLLE_SS_MAX_VAL_TEGRA210 | PLLE_SS_INC_VAL |\ + PLLE_SS_INCINTRV_VAL_TEGRA210) #define PLLE_AUX_PLLP_SEL BIT(2) #define PLLE_AUX_USE_LOCKDET BIT(3) @@ -1428,7 +1434,7 @@ static int clk_plle_tegra114_enable(struct clk_hw *hw) val = pll_readl(PLLE_SS_CTRL, pll); val &= ~(PLLE_SS_CNTL_CENTER | PLLE_SS_CNTL_INVERT); val &= ~PLLE_SS_COEFFICIENTS_MASK; - val |= PLLE_SS_COEFFICIENTS_VAL; + val |= PLLE_SS_COEFFICIENTS_VAL_TEGRA114; pll_writel(val, PLLE_SS_CTRL, pll); val &= ~(PLLE_SS_CNTL_SSC_BYP | PLLE_SS_CNTL_BYPASS_SS); pll_writel(val, PLLE_SS_CTRL, pll); @@ -2065,7 +2071,7 @@ static int clk_plle_tegra210_enable(struct clk_hw *hw) val = pll_readl(PLLE_SS_CTRL, pll); val &= ~(PLLE_SS_CNTL_CENTER | PLLE_SS_CNTL_INVERT); val &= ~PLLE_SS_COEFFICIENTS_MASK; - val |= PLLE_SS_COEFFICIENTS_VAL; + val |= PLLE_SS_COEFFICIENTS_VAL_TEGRA210; pll_writel(val, PLLE_SS_CTRL, pll); val &= ~(PLLE_SS_CNTL_SSC_BYP | PLLE_SS_CNTL_BYPASS_SS); pll_writel(val, PLLE_SS_CTRL, pll); From 047d6d8401c2d8f59ae5f478486096c13147ddf7 Mon Sep 17 00:00:00 2001 From: Amitoj Kaur Chawla Date: Sun, 24 Jan 2016 20:45:20 +0530 Subject: [PATCH 032/489] clk: tegra: Add missing of_node_put() for_each_child_of_node() performs an of_node_get() on each iteration, so before breaking out of the loop an of_node_put() is required. Found using Coccinelle. The semantic patch used for this is as follows: // @@ expression e; local idexpression child; @@ for_each_child_of_node(root, child) { ... when != of_node_put(child) when != e = child ( return child; | + of_node_put(child); ? return ...; ) ... } // Signed-off-by: Amitoj Kaur Chawla Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-emc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c index e1fe8f35d45c..74e7544f861b 100644 --- a/drivers/clk/tegra/clk-emc.c +++ b/drivers/clk/tegra/clk-emc.c @@ -450,8 +450,10 @@ static int load_timings_from_dt(struct tegra_clk_emc *tegra, struct emc_timing *timing = tegra->timings + (i++); err = load_one_timing_from_dt(tegra, timing, child); - if (err) + if (err) { + of_node_put(child); return err; + } timing->ram_code = ram_code; } @@ -499,9 +501,9 @@ struct clk *tegra_clk_register_emc(void __iomem *base, struct device_node *np, * fuses until the apbmisc driver is loaded. */ err = load_timings_from_dt(tegra, node, node_ram_code); + of_node_put(node); if (err) return ERR_PTR(err); - of_node_put(node); break; } From 29569941688cdf647f953b2eb073aa6ec9dd3fc1 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Thu, 28 Jan 2016 16:33:50 +0000 Subject: [PATCH 033/489] clk: tegra: Add the APB2APE audio clock on Tegra210 The APB2APE clock for the audio subsystem is required for powering up the audio power domain and accessing the various modules in this subsystem on Tegra210 devices. Add this clock for Tegra210. Signed-off-by: Jon Hunter Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-id.h | 1 + drivers/clk/tegra/clk-tegra-periph.c | 1 + drivers/clk/tegra/clk-tegra210.c | 1 + include/dt-bindings/clock/tegra210-car.h | 2 +- 4 files changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h index 19ce0738ee76..62ea38187b71 100644 --- a/drivers/clk/tegra/clk-id.h +++ b/drivers/clk/tegra/clk-id.h @@ -11,6 +11,7 @@ enum clk_id { tegra_clk_afi, tegra_clk_amx, tegra_clk_amx1, + tegra_clk_apb2ape, tegra_clk_apbdma, tegra_clk_apbif, tegra_clk_ape, diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c index 1860df1862dd..ea2b9cbf9e70 100644 --- a/drivers/clk/tegra/clk-tegra-periph.c +++ b/drivers/clk/tegra/clk-tegra-periph.c @@ -829,6 +829,7 @@ static struct tegra_periph_init_data gate_clks[] = { GATE("xusb_gate", "osc", 143, 0, tegra_clk_xusb_gate, 0), GATE("pll_p_out_cpu", "pll_p", 223, 0, tegra_clk_pll_p_out_cpu, 0), GATE("pll_p_out_adsp", "pll_p", 187, 0, tegra_clk_pll_p_out_adsp, 0), + GATE("apb2ape", "clk_m", 107, 0, tegra_clk_apb2ape, 0), }; static struct tegra_periph_init_data div_clks[] = { diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index ffcb86a667d9..14c1841eb29b 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -2204,6 +2204,7 @@ static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = { [tegra_clk_pll_c4_out1] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT1, .present = true }, [tegra_clk_pll_c4_out2] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT2, .present = true }, [tegra_clk_pll_c4_out3] = { .dt_id = TEGRA210_CLK_PLL_C4_OUT3, .present = true }, + [tegra_clk_apb2ape] = { .dt_id = TEGRA210_CLK_APB2APE, .present = true }, }; static struct tegra_devclk devclks[] __initdata = { diff --git a/include/dt-bindings/clock/tegra210-car.h b/include/dt-bindings/clock/tegra210-car.h index 6f45aea49e4f..0a05b0d36ae7 100644 --- a/include/dt-bindings/clock/tegra210-car.h +++ b/include/dt-bindings/clock/tegra210-car.h @@ -126,7 +126,7 @@ /* 104 */ /* 105 */ #define TEGRA210_CLK_D_AUDIO 106 -/* 107 ( affects abp -> ape) */ +#define TEGRA210_CLK_APB2APE 107 /* 108 */ /* 109 */ /* 110 */ From 4f8d44403079991a29e69f6aa25bb718ead418cb Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 18 Dec 2015 13:45:28 +0000 Subject: [PATCH 034/489] clk: tegra: Fix clock sources for Tegra210 EMC The EMC clock sources for Tegra210 currently incorrectly include pll_c2 and pll_c3. However, both of these should have been pll_mb as shown in the TRM. If Tegra210 happens to be configured such that the pll_mb is the default clock for the EMC, as configured by the bootloader, then this will cause a system hang on boot. This is because the kernel will disable the pll_mb when disabling unused clock as it appears to be unused when it is not. Also add the additional pll_p clock source for the EMC. Signed-off-by: Jon Hunter Acked-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 14c1841eb29b..429eec96696e 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -243,7 +243,8 @@ static unsigned long tegra210_input_freq[] = { }; static const char *mux_pllmcp_clkm[] = { - "pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_c2", "pll_c3", + "pll_m", "pll_c", "pll_p", "clk_m", "pll_m_ud", "pll_mb", "pll_mb", + "pll_p", }; #define mux_pllmcp_clkm_idx NULL From 0649c3232be5b647dba50e2f6d31fe1306913ab2 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 21 Dec 2015 12:56:31 +0000 Subject: [PATCH 035/489] clk: tegra: Fix warning caused by pll_u failing to lock If the pll_u is not configured by the bootloader, then on kernel boot the following warning is seen: clk_pll_wait_for_lock: Timed out waiting for pll pll_u_vco lock tegra_init_from_table: Failed to enable pll_u_out1 ------------[ cut here ]------------ WARNING: at drivers/clk/tegra/clk.c:269 Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.4.0-rc4-next-20151214+ #1 Hardware name: NVIDIA Tegra210 P2371 reference board (E.1) (DT) task: ffffffc0bc0a0000 ti: ffffffc0bc0a8000 task.ti: ffffffc0bc0a8000 PC is at tegra_init_from_table+0x140/0x164 LR is at tegra_init_from_table+0x140/0x164 pc : [] lr : [] pstate: 80000045 sp : ffffffc0bc0abd50 x29: ffffffc0bc0abd50 x28: ffffffc00090b8a8 x27: ffffffc000a06000 x26: ffffffc0bc019780 x25: ffffffc00086a708 x24: ffffffc00086a790 x23: ffffffc0006d7188 x22: ffffffc0bc010000 x21: 000000000000016e x20: ffffffc0bc00d100 x19: ffffffc000944178 x18: 0000000000000007 x17: 000000000000000e x16: 0000000000000001 x15: 0000000000000007 x14: 000000000000000e x13: 0000000000000013 x12: 000000000000001a x11: 000000000000004d x10: 0000000000000750 x9 : ffffffc0bc0a8000 x8 : ffffffc0bc0a07b0 x7 : 0000000000000001 x6 : 0000000002d5f0f8 x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000002 x2 : ffffffc000996724 x1 : 0000000000000000 x0 : 0000000000000032 ---[ end trace cbd20ae519e92ced ]--- Call trace: [] tegra_init_from_table+0x140/0x164 [] tegra210_clock_apply_init_table+0x20/0x28 [] tegra_clocks_apply_init_table+0x18/0x24 [] do_one_initcall+0x90/0x194 [] kernel_init_freeable+0x148/0x1e8 [] kernel_init+0x10/0xdc [] ret_from_fork+0x10/0x40 clk_pll_wait_for_lock: Timed out waiting for pll pll_u_vco lock tegra_init_from_table: Failed to enable pll_u_out2 ------------[ cut here ]------------ pll_u can be either controlled by software or hardware and this is selected via the OVERRIDE bit in the pll_u base register. In the function tegra210_pll_init(), the OVERRIDE bit for pll_u is cleared, which selects hardware control of the pll. However, at the same time the pll_u clocks are populated in the init_table for tegra210 and so software will try to configure the pll_u if it is not already configured and hence, the above warning is seen when the pll fails to lock. Remove the pll_u clocks from the init_table so that software does not try to configure this pll on boot. Signed-off-by: Jon Hunter Acked-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 429eec96696e..1948ea4f77ff 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -2726,8 +2726,6 @@ static struct tegra_clk_init_table init_table[] __initdata = { { TEGRA210_CLK_DFLL_REF, TEGRA210_CLK_PLL_P, 51000000, 1 }, { TEGRA210_CLK_SBC4, TEGRA210_CLK_PLL_P, 12000000, 1 }, { TEGRA210_CLK_PLL_RE_VCO, TEGRA210_CLK_CLK_MAX, 672000000, 1 }, - { TEGRA210_CLK_PLL_U_OUT1, TEGRA210_CLK_CLK_MAX, 48000000, 1 }, - { TEGRA210_CLK_PLL_U_OUT2, TEGRA210_CLK_CLK_MAX, 60000000, 1 }, { TEGRA210_CLK_XUSB_GATE, TEGRA210_CLK_CLK_MAX, 0, 1 }, { TEGRA210_CLK_XUSB_SS_SRC, TEGRA210_CLK_PLL_U_480M, 120000000, 0 }, { TEGRA210_CLK_XUSB_FS_SRC, TEGRA210_CLK_PLL_U_48M, 48000000, 0 }, From 2d5b6cf84a1764aa9837128bc1e6fd53cb0bb9c1 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Mon, 21 Dec 2015 12:56:32 +0000 Subject: [PATCH 036/489] clk: tegra: Use definition for pll_u override bit The definition, PLLU_BASE_OVERRIDE, for the pll_u OVERRIDE bit is defined but not used and when the OVERRIDE bit is cleared in tegra210_pll_init() the code directly uses the bit number. Therefore, use the definition, PLLU_BASE_OVERRIDE when clearing the OVERRIDE bit. Signed-off-by: Jon Hunter Acked-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 1948ea4f77ff..ca04c2d85e2b 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -2507,7 +2507,7 @@ static void __init tegra210_pll_init(void __iomem *clk_base, /* PLLU_VCO */ val = readl(clk_base + pll_u_vco_params.base_reg); - val &= ~BIT(24); /* disable PLLU_OVERRIDE */ + val &= ~PLLU_BASE_OVERRIDE; /* disable PLLU_OVERRIDE */ writel(val, clk_base + pll_u_vco_params.base_reg); clk = tegra_clk_register_pllre("pll_u_vco", "pll_ref", clk_base, pmc, From d9e657919afe0794713b5ffb069f9f66c37bfe17 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 4 Dec 2015 17:04:23 +0000 Subject: [PATCH 037/489] clk: tegra: Fix sparse warning for pll_m Sparse generates the following warning for the pll_m params structure: drivers/clk/tegra/clk-tegra210.c:1569:10: warning: Initializer entry defined twice drivers/clk/tegra/clk-tegra210.c:1570:10: also defined here Fix this by correcting the index for the MISC1 register. Fixes: b31eba5ff3f7 ("clk: tegra: Add support for Tegra210 clocks") Signed-off-by: Jon Hunter Acked-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index ca04c2d85e2b..271ea1580d91 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -1566,7 +1566,7 @@ static struct tegra_clk_pll_params pll_m_params = { .iddq_bit_idx = PLLM_IDDQ_BIT, .max_p = PLL_QLIN_PDIV_MAX, .ext_misc_reg[0] = PLLM_MISC2, - .ext_misc_reg[0] = PLLM_MISC1, + .ext_misc_reg[1] = PLLM_MISC1, .round_p_to_pdiv = pll_qlin_p_to_pdiv, .pdiv_tohw = pll_qlin_pdiv_to_hw, .div_nmp = &pllm_nmp, From fd360e20844aa8d1081eb28c72128abb7a5d3598 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 4 Dec 2015 17:04:24 +0000 Subject: [PATCH 038/489] clk: tegra: Fix sparse warnings for functions not declared as static Sparse reports the following warnings for functions in clk-tegra210.c that should be declared as static: drivers/clk/tegra/clk-tegra210.c:460:6: warning: symbol 'tegra210_pllcx_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:485:6: warning: symbol '_pllc_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:490:6: warning: symbol '_pllc2_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:495:6: warning: symbol '_pllc3_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:500:6: warning: symbol '_plla1_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:510:6: warning: symbol 'tegra210_plla_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:562:6: warning: symbol 'tegra210_plld_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:701:6: warning: symbol 'tegra210_plld2_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:709:6: warning: symbol 'tegra210_plldp_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:722:6: warning: symbol 'tegra210_pllc4_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:731:6: warning: symbol 'tegra210_pllre_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:844:6: warning: symbol 'tegra210_pllx_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:904:6: warning: symbol 'tegra210_pllmb_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:963:6: warning: symbol 'tegra210_pllp_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:1025:6: warning: symbol 'tegra210_pllu_set_defaults' was not declared. Should it be static? drivers/clk/tegra/clk-tegra210.c:1215:15: warning: symbol 'tegra210_clk_adjust_vco_min' was not declared. Should it be static? Fix this by declaring the above as static. Signed-off-by: Jon Hunter Acked-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra210.c | 36 +++++++++++++++++--------------- 1 file changed, 19 insertions(+), 17 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c index 271ea1580d91..637041fd53ad 100644 --- a/drivers/clk/tegra/clk-tegra210.c +++ b/drivers/clk/tegra/clk-tegra210.c @@ -458,7 +458,8 @@ static void pllcx_check_defaults(struct tegra_clk_pll_params *params) PLLCX_MISC3_WRITE_MASK); } -void tegra210_pllcx_set_defaults(const char *name, struct tegra_clk_pll *pllcx) +static void tegra210_pllcx_set_defaults(const char *name, + struct tegra_clk_pll *pllcx) { pllcx->params->defaults_set = true; @@ -483,22 +484,22 @@ void tegra210_pllcx_set_defaults(const char *name, struct tegra_clk_pll *pllcx) udelay(1); } -void _pllc_set_defaults(struct tegra_clk_pll *pllcx) +static void _pllc_set_defaults(struct tegra_clk_pll *pllcx) { tegra210_pllcx_set_defaults("PLL_C", pllcx); } -void _pllc2_set_defaults(struct tegra_clk_pll *pllcx) +static void _pllc2_set_defaults(struct tegra_clk_pll *pllcx) { tegra210_pllcx_set_defaults("PLL_C2", pllcx); } -void _pllc3_set_defaults(struct tegra_clk_pll *pllcx) +static void _pllc3_set_defaults(struct tegra_clk_pll *pllcx) { tegra210_pllcx_set_defaults("PLL_C3", pllcx); } -void _plla1_set_defaults(struct tegra_clk_pll *pllcx) +static void _plla1_set_defaults(struct tegra_clk_pll *pllcx) { tegra210_pllcx_set_defaults("PLL_A1", pllcx); } @@ -508,7 +509,7 @@ void _plla1_set_defaults(struct tegra_clk_pll *pllcx) * PLL with dynamic ramp and fractional SDM. Dynamic ramp is not used. * Fractional SDM is allowed to provide exact audio rates. */ -void tegra210_plla_set_defaults(struct tegra_clk_pll *plla) +static void tegra210_plla_set_defaults(struct tegra_clk_pll *plla) { u32 mask; u32 val = readl_relaxed(clk_base + plla->params->base_reg); @@ -560,7 +561,7 @@ void tegra210_plla_set_defaults(struct tegra_clk_pll *plla) * PLLD * PLL with fractional SDM. */ -void tegra210_plld_set_defaults(struct tegra_clk_pll *plld) +static void tegra210_plld_set_defaults(struct tegra_clk_pll *plld) { u32 val; u32 mask = 0xffff; @@ -699,7 +700,7 @@ static void plldss_defaults(const char *pll_name, struct tegra_clk_pll *plldss, udelay(1); } -void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2) +static void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2) { plldss_defaults("PLL_D2", plld2, PLLD2_MISC0_DEFAULT_VALUE, PLLD2_MISC1_CFG_DEFAULT_VALUE, @@ -707,7 +708,7 @@ void tegra210_plld2_set_defaults(struct tegra_clk_pll *plld2) PLLD2_MISC3_CTRL2_DEFAULT_VALUE); } -void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp) +static void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp) { plldss_defaults("PLL_DP", plldp, PLLDP_MISC0_DEFAULT_VALUE, PLLDP_MISC1_CFG_DEFAULT_VALUE, @@ -720,7 +721,7 @@ void tegra210_plldp_set_defaults(struct tegra_clk_pll *plldp) * Base and misc0 layout is the same as PLLD2/PLLDP, but no SDM/SSC support. * VCO is exposed to the clock tree via fixed 1/3 and 1/5 dividers. */ -void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4) +static void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4) { plldss_defaults("PLL_C4", pllc4, PLLC4_MISC0_DEFAULT_VALUE, 0, 0, 0); } @@ -729,7 +730,7 @@ void tegra210_pllc4_set_defaults(struct tegra_clk_pll *pllc4) * PLLRE * VCO is exposed to the clock tree directly along with post-divider output */ -void tegra210_pllre_set_defaults(struct tegra_clk_pll *pllre) +static void tegra210_pllre_set_defaults(struct tegra_clk_pll *pllre) { u32 mask; u32 val = readl_relaxed(clk_base + pllre->params->base_reg); @@ -842,7 +843,7 @@ static void pllx_check_defaults(struct tegra_clk_pll *pll) PLLX_MISC5_WRITE_MASK); } -void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx) +static void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx) { u32 val; u32 step_a, step_b; @@ -902,7 +903,7 @@ void tegra210_pllx_set_defaults(struct tegra_clk_pll *pllx) } /* PLLMB */ -void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb) +static void tegra210_pllmb_set_defaults(struct tegra_clk_pll *pllmb) { u32 mask, val = readl_relaxed(clk_base + pllmb->params->base_reg); @@ -961,7 +962,7 @@ static void pllp_check_defaults(struct tegra_clk_pll *pll, bool enabled) ~mask & PLLP_MISC1_WRITE_MASK); } -void tegra210_pllp_set_defaults(struct tegra_clk_pll *pllp) +static void tegra210_pllp_set_defaults(struct tegra_clk_pll *pllp) { u32 mask; u32 val = readl_relaxed(clk_base + pllp->params->base_reg); @@ -1023,7 +1024,7 @@ static void pllu_check_defaults(struct tegra_clk_pll *pll, bool hw_control) ~mask & PLLU_MISC1_WRITE_MASK); } -void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu) +static void tegra210_pllu_set_defaults(struct tegra_clk_pll *pllu) { u32 val = readl_relaxed(clk_base + pllu->params->base_reg); @@ -1213,8 +1214,9 @@ static void tegra210_clk_pll_set_gain(struct tegra_clk_pll_freq_table *cfg) cfg->m *= PLL_SDM_COEFF; } -unsigned long tegra210_clk_adjust_vco_min(struct tegra_clk_pll_params *params, - unsigned long parent_rate) +static unsigned long +tegra210_clk_adjust_vco_min(struct tegra_clk_pll_params *params, + unsigned long parent_rate) { unsigned long vco_min = params->vco_min; From 5a1d5eff3ede4de4482015a9999336051054283f Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Fri, 4 Dec 2015 17:04:25 +0000 Subject: [PATCH 039/489] clk: tegra: super: Fix sparse warnings for functions not declared as static Sparse reports the following warnings for structures and functions that should be declared static: drivers/clk/tegra/clk-tegra-super-gen4.c:70:35: warning: symbol 'tegra_super_gen_info_gen4' was not declared. Should it be static? drivers/clk/tegra/clk-tegra-super-gen4.c:96:35: warning: symbol 'tegra_super_gen_info_gen5' was not declared. Should it be static? drivers/clk/tegra/clk-tegra-super-gen4.c:174:13: warning: symbol 'tegra_super_clk_init' was not declared. Should it be static? Fix this by making the above static. Signed-off-by: Jon Hunter Acked-by: Rhyland Klein Signed-off-by: Thierry Reding --- drivers/clk/tegra/clk-tegra-super-gen4.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/clk/tegra/clk-tegra-super-gen4.c b/drivers/clk/tegra/clk-tegra-super-gen4.c index 4559a20e3af6..474de0f0c26d 100644 --- a/drivers/clk/tegra/clk-tegra-super-gen4.c +++ b/drivers/clk/tegra/clk-tegra-super-gen4.c @@ -67,7 +67,7 @@ static const char *cclk_lp_parents[] = { "clk_m", "pll_c", "clk_32k", "pll_m", "pll_p", "pll_p_out4", "unused", "unused", "pll_x", "pll_x_out0" }; -const struct tegra_super_gen_info tegra_super_gen_info_gen4 = { +static const struct tegra_super_gen_info tegra_super_gen_info_gen4 = { .gen = gen4, .sclk_parents = sclk_parents, .cclk_g_parents = cclk_g_parents, @@ -93,7 +93,7 @@ static const char *cclk_lp_parents_gen5[] = { "clk_m", "unused", "clk_32k", "unu "unused", "unused", "unused", "unused", "dfllCPU_out" }; -const struct tegra_super_gen_info tegra_super_gen_info_gen5 = { +static const struct tegra_super_gen_info tegra_super_gen_info_gen5 = { .gen = gen5, .sclk_parents = sclk_parents_gen5, .cclk_g_parents = cclk_g_parents_gen5, @@ -171,7 +171,7 @@ static void __init tegra_sclk_init(void __iomem *clk_base, *dt_clk = clk; } -void __init tegra_super_clk_init(void __iomem *clk_base, +static void __init tegra_super_clk_init(void __iomem *clk_base, void __iomem *pmc_base, struct tegra_clk *tegra_clks, struct tegra_clk_pll_params *params, From 16c6d048d7b74249a4387700887e8adb13028866 Mon Sep 17 00:00:00 2001 From: Wenwei Tao Date: Thu, 4 Feb 2016 15:13:23 +0100 Subject: [PATCH 040/489] lightnvm: put bio before return MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The bio is not returned if the data page cannot be allocated. Signed-off-by: Wenwei Tao Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/lightnvm/rrpc.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c index d8c75958ced3..307db1ea22de 100644 --- a/drivers/lightnvm/rrpc.c +++ b/drivers/lightnvm/rrpc.c @@ -300,8 +300,10 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk) } page = mempool_alloc(rrpc->page_pool, GFP_NOIO); - if (!page) + if (!page) { + bio_put(bio); return -ENOMEM; + } while ((slot = find_first_zero_bit(rblk->invalid_pages, nr_pgs_per_blk)) < nr_pgs_per_blk) { From bba7f40a029c1e2966146e3a021b3deaf5639904 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Thu, 4 Feb 2016 15:13:24 +0100 Subject: [PATCH 041/489] lightnvm: warn if irqs are disabled in lock laddr MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a warning if irqs are disabled when locking a new address in rrpc. The typical path to a new request does not disable irqs, but this is not guaranteed in the future. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/lightnvm/rrpc.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/lightnvm/rrpc.h b/drivers/lightnvm/rrpc.h index ef13ac7700c8..b0277cbf93d6 100644 --- a/drivers/lightnvm/rrpc.h +++ b/drivers/lightnvm/rrpc.h @@ -184,6 +184,8 @@ static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr, sector_t laddr_end = laddr + pages - 1; struct rrpc_inflight_rq *rtmp; + WARN_ON(irqs_disabled()); + spin_lock_irq(&rrpc->inflights.lock); list_for_each_entry(rtmp, &rrpc->inflights.reqs, list) { if (unlikely(request_intersects(rtmp, laddr, laddr_end))) { From 3704e098cc1a4c2cabcf4e1cfbbff38b4bfb1ea7 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Javier=20Gonz=C3=A1lez?= Date: Thu, 4 Feb 2016 15:13:25 +0100 Subject: [PATCH 042/489] lightnvm: fix request intersection locking in rrpc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This patch fixes an error on the calculation of intersecting logical addresses; it contemplates the case where a new request including several addresses intersects with a single locked address. This case is typical when multiple pages are sent in a new request, while GC - which at the moment sends one address at the time - is running. Signed-off-by: Javier González Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/lightnvm/rrpc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/lightnvm/rrpc.h b/drivers/lightnvm/rrpc.h index b0277cbf93d6..f7b37336353f 100644 --- a/drivers/lightnvm/rrpc.h +++ b/drivers/lightnvm/rrpc.h @@ -174,8 +174,7 @@ static inline sector_t rrpc_get_sector(sector_t laddr) static inline int request_intersects(struct rrpc_inflight_rq *r, sector_t laddr_start, sector_t laddr_end) { - return (laddr_end >= r->l_start && laddr_end <= r->l_end) && - (laddr_start >= r->l_start && laddr_start <= r->l_end); + return (laddr_end >= r->l_start) && (laddr_start <= r->l_end); } static int __rrpc_lock_laddr(struct rrpc *rrpc, sector_t laddr, From 6dde1d6c9094a7c20a680aa2196ad6d032ec7ded Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 4 Feb 2016 15:13:26 +0100 Subject: [PATCH 043/489] lightnvm: check overflow and correct mlc pairs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The specification currently limits the number of MLC pairs to 886. Make sure that a device is unable to be instantiate if more is configured. Also, previously the patch had the wrong math for copying MLC pairs, as it only copied half of the actual entries. Fixes: ca5927e7ab53 "lightnvm: introduce mlc lower page table mappings" Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/nvme/host/lightnvm.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index 5cd3725e2fa4..6bb15e4926dc 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -146,9 +146,10 @@ struct nvme_nvm_command { }; }; +#define NVME_NVM_LP_MLC_PAIRS 886 struct nvme_nvm_lp_mlc { __u16 num_pairs; - __u8 pairs[886]; + __u8 pairs[NVME_NVM_LP_MLC_PAIRS]; }; struct nvme_nvm_lp_tbl { @@ -282,9 +283,14 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id) memcpy(dst->lptbl.id, src->lptbl.id, 8); dst->lptbl.mlc.num_pairs = le16_to_cpu(src->lptbl.mlc.num_pairs); - /* 4 bits per pair */ + + if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) { + pr_err("nvm: number of MLC pairs not supported\n"); + return -EINVAL; + } + memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs, - dst->lptbl.mlc.num_pairs >> 1); + dst->lptbl.mlc.num_pairs); } } From bf64318564c43385ffc3d3dfedab5287bdf3dfdd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 4 Feb 2016 15:13:27 +0100 Subject: [PATCH 044/489] lightnvm: allow to force mm initialization MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit System block allows the device to initialize with its configured media manager. The system blocks is written to disk, and read again when media manager is determined. For this to work, the backend must store the data. Device drivers, such as null_blk, does not have any backend storage. This patch allows the media manager to be initialized without a storage backend. It also fix incorrect configuration of capabilities in null_blk, as it does not support get/set bad block interface. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/block/null_blk.c | 2 +- drivers/lightnvm/core.c | 25 ++++++++++++++++--------- include/linux/lightnvm.h | 4 ++++ 3 files changed, 21 insertions(+), 10 deletions(-) diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 8ba1e97d573c..ae05d31c0559 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -478,7 +478,7 @@ static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id) id->ver_id = 0x1; id->vmnt = 0; id->cgrps = 1; - id->cap = 0x3; + id->cap = 0x2; id->dom = 0x1; id->ppaf.blk_offset = 0; diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 33224cb91c5b..9f6acd5d1d2e 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -572,11 +572,13 @@ int nvm_register(struct request_queue *q, char *disk_name, } } - ret = nvm_get_sysblock(dev, &dev->sb); - if (!ret) - pr_err("nvm: device not initialized.\n"); - else if (ret < 0) - pr_err("nvm: err (%d) on device initialization\n", ret); + if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) { + ret = nvm_get_sysblock(dev, &dev->sb); + if (!ret) + pr_err("nvm: device not initialized.\n"); + else if (ret < 0) + pr_err("nvm: err (%d) on device initialization\n", ret); + } /* register device with a supported media manager */ down_write(&nvm_lock); @@ -1055,9 +1057,11 @@ static long __nvm_ioctl_dev_init(struct nvm_ioctl_dev_init *init) strncpy(info.mmtype, init->mmtype, NVM_MMTYPE_LEN); info.fs_ppa.ppa = -1; - ret = nvm_init_sysblock(dev, &info); - if (ret) - return ret; + if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) { + ret = nvm_init_sysblock(dev, &info); + if (ret) + return ret; + } memcpy(&dev->sb, &info, sizeof(struct nvm_sb_info)); @@ -1117,7 +1121,10 @@ static long nvm_ioctl_dev_factory(struct file *file, void __user *arg) dev->mt = NULL; } - return nvm_dev_factory(dev, fact.flags); + if (dev->identity.cap & NVM_ID_DCAP_BBLKMGMT) + return nvm_dev_factory(dev, fact.flags); + + return 0; } static long nvm_ctl_ioctl(struct file *file, uint cmd, unsigned long arg) diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index d6750111e48e..2190419bdf0a 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -135,6 +135,10 @@ enum { /* Memory types */ NVM_ID_FMTYPE_SLC = 0, NVM_ID_FMTYPE_MLC = 1, + + /* Device capabilities */ + NVM_ID_DCAP_BBLKMGMT = 0x1, + NVM_UD_DCAP_ECC = 0x2, }; struct nvm_id_lp_mlc { From eceb3e61c74356590f37cec89708770b333162c4 Mon Sep 17 00:00:00 2001 From: Biao Huang Date: Wed, 3 Feb 2016 09:24:45 +0800 Subject: [PATCH 045/489] pinctrl: mediatek: fix direction control issue Since input-enable/disable and input-schmitt-enable/disable are workable when gpio direction is input, so add direction setting when do input-enable/disable and input-schmitt-enable/disable properties. Signed-off-by: Biao Huang Signed-off-by: Linus Walleij --- drivers/pinctrl/mediatek/pinctrl-mtk-common.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c index 16d48a4ed225..e96e86d2e745 100644 --- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c +++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c @@ -347,6 +347,7 @@ static int mtk_pconf_parse_conf(struct pinctrl_dev *pctldev, ret = mtk_pconf_set_pull_select(pctl, pin, true, false, arg); break; case PIN_CONFIG_INPUT_ENABLE: + mtk_pmx_gpio_set_direction(pctldev, NULL, pin, true); ret = mtk_pconf_set_ies_smt(pctl, pin, arg, param); break; case PIN_CONFIG_OUTPUT: @@ -354,6 +355,7 @@ static int mtk_pconf_parse_conf(struct pinctrl_dev *pctldev, ret = mtk_pmx_gpio_set_direction(pctldev, NULL, pin, false); break; case PIN_CONFIG_INPUT_SCHMITT_ENABLE: + mtk_pmx_gpio_set_direction(pctldev, NULL, pin, true); ret = mtk_pconf_set_ies_smt(pctl, pin, arg, param); break; case PIN_CONFIG_DRIVE_STRENGTH: From d76d65fd26951498144029c24852c4d54ee512d9 Mon Sep 17 00:00:00 2001 From: Larry Finger Date: Mon, 1 Feb 2016 12:58:54 -0600 Subject: [PATCH 046/489] rtlwifi: fix broken VHT support When using a 5G-capable device with VHT (802.11ac) rates enabled was not working (packets were not delivered) and the following mac80211 warning was printed: WARNING: CPU: 3 PID: 2253 at net/mac80211/rate.c:625 ieee80211_get_tx_rates+0x22e/0x620 [mac80211]() Modules linked in: rtl8821ae btcoexist rtl_pci rtlwifi fuse drbg ansi_cprng ctr ccm bnep bluetooth af_packet nfs fscache vboxpci(O) vboxnetadp(O) vboxne tflt(O) vboxdrv(O) arc4 snd_hda_codec_generic x86_pkg_temp_thermal rtsx_pci_sdmmc mmc_core rtsx_pci_ms kvm_intel memstick iwlmvm kvm mac80211 snd_hda_intel snd_hda_cod ec snd_hwdep snd_hda_core irqbypass snd_pcm iwlwifi crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel aesni_intel aes_x86_64 snd_timer lrw gf128mul glue_h elper ablk_helper cryptd snd cfg80211 pcspkr serio_raw e1000e rtsx_pci lpc_ich ptp xhci_pci mfd_core pps_core xhci_hcd soundcore toshiba_acpi thermal sparse_keymap wmi toshiba_bluetooth rfkill acpi_cpufreq battery ac processor dm_mod i915 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops drm sr_mod cdrom video button sg autofs4 [last unloaded: rtlwifi] CPU: 3 PID: 2253 Comm: Timer Tainted: G W O 4.5.0-rc1-wl+ #79 Hardware name: TOSHIBA TECRA A50-A/TECRA A50-A, BIOS Version 4.20 04/17/2014 ffffffffa05c4be6 ffff8802262036d8 ffffffff813d7912 0000000000000000 ffff880226203710 ffffffff8106bcb6 ffff8800c6831300 ffff8800c6831330 0000000000000000 ffff8800c683133c ffff880065923638 ffff880226203720 Call Trace: [] dump_stack+0x4b/0x79 [] warn_slowpath_common+0x86/0xc0 [] warn_slowpath_null+0x1a/0x20 [] ieee80211_get_tx_rates+0x22e/0x620 [mac80211] [] ? rtl_is_special_data+0x32/0x240 [rtlwifi] [] ? rate_control_get_rate+0xce/0x150 [mac80211] [] ? trace_hardirqs_on+0xd/0x10 [] ? __local_bh_enable_ip+0x65/0xd0 Signed-off-by: Kalle Valo --- drivers/net/wireless/realtek/rtlwifi/rc.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/realtek/rtlwifi/rc.c b/drivers/net/wireless/realtek/rtlwifi/rc.c index 74c14ce28238..28f7010e7108 100644 --- a/drivers/net/wireless/realtek/rtlwifi/rc.c +++ b/drivers/net/wireless/realtek/rtlwifi/rc.c @@ -138,6 +138,11 @@ static void _rtl_rc_rate_set_series(struct rtl_priv *rtlpriv, ((wireless_mode == WIRELESS_MODE_N_5G) || (wireless_mode == WIRELESS_MODE_N_24G))) rate->flags |= IEEE80211_TX_RC_MCS; + if (sta && sta->vht_cap.vht_supported && + (wireless_mode == WIRELESS_MODE_AC_5G || + wireless_mode == WIRELESS_MODE_AC_24G || + wireless_mode == WIRELESS_MODE_AC_ONLY)) + rate->flags |= IEEE80211_TX_RC_VHT_MCS; } } From 09954bad448791ef01202351d437abdd9497a804 Mon Sep 17 00:00:00 2001 From: Jiri Kosina Date: Sat, 6 Feb 2016 23:00:22 +0100 Subject: [PATCH 047/489] floppy: refactor open() flags handling In case /dev/fdX is open with O_NDELAY / O_NONBLOCK, floppy_open() immediately succeeds, without performing any further media / controller preparations. That's "correct" wrt. the NODELAY flag, but is hardly correct wrt. the rest of the floppy driver, that is not really O_NONBLOCK ready, at all. Therefore it's not too surprising, that subsequent attempts to work with the filedescriptor produce bad results. Namely, syzkaller tool has been able to livelock mmap() on the returned fd to keep waiting on the page unlock bit forever. Quite frankly, I have trouble defining what non-blocking behavior would be for floppies. Is waiting ages for the driver to actually succeed reading a sector blocking operation? Is waiting for drive motor to start blocking operation? How about in case of virtualized floppies? One option would be returning EWOULDBLOCK in case O_NDLEAY / O_NONBLOCK is being passed to open(). That has a theoretical potential of breaking some arcane and archaic userspace though. Let's take a more conservative aproach, and accept the O_NDLEAY flag, and let the driver behave as usual. While at it, clean up a bit handling of !(mode & (FMODE_READ|FMODE_WRITE)) case and return EINVAL instead of succeeding as well. Spotted by syzkaller tool. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Jiri Kosina --- drivers/block/floppy.c | 34 +++++++++++++++++++--------------- 1 file changed, 19 insertions(+), 15 deletions(-) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index b206115d761c..84708a5f8c52 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3663,6 +3663,11 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) opened_bdev[drive] = bdev; + if (!(mode & (FMODE_READ|FMODE_WRITE))) { + res = -EINVAL; + goto out; + } + res = -ENXIO; if (!floppy_track_buffer) { @@ -3706,21 +3711,20 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) if (UFDCS->rawcmd == 1) UFDCS->rawcmd = 2; - if (!(mode & FMODE_NDELAY)) { - if (mode & (FMODE_READ|FMODE_WRITE)) { - UDRS->last_checked = 0; - clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); - check_disk_change(bdev); - if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) - goto out; - if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) - goto out; - } - res = -EROFS; - if ((mode & FMODE_WRITE) && - !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) - goto out; - } + UDRS->last_checked = 0; + clear_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags); + check_disk_change(bdev); + if (test_bit(FD_DISK_CHANGED_BIT, &UDRS->flags)) + goto out; + if (test_bit(FD_OPEN_SHOULD_FAIL_BIT, &UDRS->flags)) + goto out; + + res = -EROFS; + + if ((mode & FMODE_WRITE) && + !test_bit(FD_DISK_WRITABLE_BIT, &UDRS->flags)) + goto out; + mutex_unlock(&open_lock); mutex_unlock(&floppy_mutex); return 0; From 28b4c263961c47da84ed8b5be0b5116bad1133eb Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sun, 7 Feb 2016 19:35:05 -0500 Subject: [PATCH 048/489] ext4 crypto: revalidate dentry after adding or removing the key Add a validation check for dentries for encrypted directory to make sure we're not caching stale data after a key has been added or removed. Also check to make sure that status of the encryption key is updated when readdir(2) is executed. Signed-off-by: Theodore Ts'o --- fs/ext4/crypto.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++ fs/ext4/dir.c | 6 ++++++ fs/ext4/ext4.h | 1 + fs/ext4/namei.c | 18 ++++++++++++++++ 4 files changed, 81 insertions(+) diff --git a/fs/ext4/crypto.c b/fs/ext4/crypto.c index c8021208a7eb..38f7562489bb 100644 --- a/fs/ext4/crypto.c +++ b/fs/ext4/crypto.c @@ -467,3 +467,59 @@ uint32_t ext4_validate_encryption_key_size(uint32_t mode, uint32_t size) return size; return 0; } + +/* + * Validate dentries for encrypted directories to make sure we aren't + * potentially caching stale data after a key has been added or + * removed. + */ +static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags) +{ + struct inode *dir = d_inode(dentry->d_parent); + struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info; + int dir_has_key, cached_with_key; + + if (!ext4_encrypted_inode(dir)) + return 0; + + if (ci && ci->ci_keyring_key && + (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) | + (1 << KEY_FLAG_REVOKED) | + (1 << KEY_FLAG_DEAD)))) + ci = NULL; + + /* this should eventually be an flag in d_flags */ + cached_with_key = dentry->d_fsdata != NULL; + dir_has_key = (ci != NULL); + + /* + * If the dentry was cached without the key, and it is a + * negative dentry, it might be a valid name. We can't check + * if the key has since been made available due to locking + * reasons, so we fail the validation so ext4_lookup() can do + * this check. + * + * We also fail the validation if the dentry was created with + * the key present, but we no longer have the key, or vice versa. + */ + if ((!cached_with_key && d_is_negative(dentry)) || + (!cached_with_key && dir_has_key) || + (cached_with_key && !dir_has_key)) { +#if 0 /* Revalidation debug */ + char buf[80]; + char *cp = simple_dname(dentry, buf, sizeof(buf)); + + if (IS_ERR(cp)) + cp = (char *) "???"; + pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata, + cached_with_key, d_is_negative(dentry), + dir_has_key); +#endif + return 0; + } + return 1; +} + +const struct dentry_operations ext4_encrypted_d_ops = { + .d_revalidate = ext4_d_revalidate, +}; diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 1d1bca74f844..6d17f31a31d7 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -111,6 +111,12 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) int dir_has_error = 0; struct ext4_str fname_crypto_str = {.name = NULL, .len = 0}; + if (ext4_encrypted_inode(inode)) { + err = ext4_get_encryption_info(inode); + if (err && err != -ENOKEY) + return err; + } + if (is_dx_dir(inode)) { err = ext4_dx_readdir(file, ctx); if (err != ERR_BAD_DX_DIR) { diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 0662b285dc8a..157b458a69d4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2302,6 +2302,7 @@ struct page *ext4_encrypt(struct inode *inode, int ext4_decrypt(struct page *page); int ext4_encrypted_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len); +extern const struct dentry_operations ext4_encrypted_d_ops; #ifdef CONFIG_EXT4_FS_ENCRYPTION int ext4_init_crypto(void); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 06574dd77614..5de8483f0062 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1558,6 +1558,24 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi struct ext4_dir_entry_2 *de; struct buffer_head *bh; + if (ext4_encrypted_inode(dir)) { + int res = ext4_get_encryption_info(dir); + + /* + * This should be a properly defined flag for + * dentry->d_flags when we uplift this to the VFS. + * d_fsdata is set to (void *) 1 if if the dentry is + * created while the directory was encrypted and we + * don't have access to the key. + */ + dentry->d_fsdata = NULL; + if (ext4_encryption_info(dir)) + dentry->d_fsdata = (void *) 1; + d_set_d_op(dentry, &ext4_encrypted_d_ops); + if (res && res != -ENOKEY) + return ERR_PTR(res); + } + if (dentry->d_name.len > EXT4_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); From 3efaf2a9a053bce452cec8d4c14f7ad6912215c9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 29 Jan 2016 16:27:07 +0200 Subject: [PATCH 049/489] dmaengine: dw: pci: add ID for WildcatPoint PCH WildcatPoint PCH as seen on MacBook 12-inch (Early 2015) has PCI enabled DesignWare DMA controller. Enable it by adding its ID to the corresponding driver. Reported-by: Leif Liddy BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=110901 Signed-off-by: Andy Shevchenko Signed-off-by: Vinod Koul --- drivers/dma/dw/pci.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/dma/dw/pci.c b/drivers/dma/dw/pci.c index 4c30fdd092b3..358f9689a3f5 100644 --- a/drivers/dma/dw/pci.c +++ b/drivers/dma/dw/pci.c @@ -108,6 +108,10 @@ static const struct pci_device_id dw_pci_id_table[] = { /* Haswell */ { PCI_VDEVICE(INTEL, 0x9c60) }, + + /* Broadwell */ + { PCI_VDEVICE(INTEL, 0x9ce0) }, + { } }; MODULE_DEVICE_TABLE(pci, dw_pci_id_table); From 4ac31d18e4125eb2970e69069a15308cbb8e4486 Mon Sep 17 00:00:00 2001 From: John Ogness Date: Thu, 28 Jan 2016 11:29:08 +0100 Subject: [PATCH 050/489] dmaengine: edma: fix residue race for cyclic When retrieving the residue value, the SRC/DST fields of the active PaRAM are read to determine the current position of the DMA engine. However, the AM335x Technical Reference Manual states: 11.3.3.6 Parameter Set Updates After the TR is read from the PaRAM (and is in the process of being submitted to the EDMA3TC), the following fields are updated as needed: ... SRC DST This means SRC/DST is incremented even though the DMA transfer may not have started yet or is in progress. Thus if the reader of the residue accesses the DMA buffer too quickly, the CPU is misinformed about the data that has been successfully processed. The CCSTAT.ACTV register is a boolean that is set if any TR is being processed by either the EMDA3CC or EDMA3TC. By polling this register it is possible to ensure that the residue value returned is valid for immediate processing. However, since the DMA engine may be active, polling may never hit a moment where no TR is being processed. To handle this, the SRC/DST is also polled to see if it changes. And as a last resort, a max loop count for the busy waiting exists to avoid an infinite loop. Signed-off-by: John Ogness Acked-by: Peter Ujfalusi Signed-off-by: Vinod Koul --- drivers/dma/edma.c | 41 ++++++++++++++++++++++++++++++++++++++++- 1 file changed, 40 insertions(+), 1 deletion(-) diff --git a/drivers/dma/edma.c b/drivers/dma/edma.c index d92d65549406..e3d7fcb69b4c 100644 --- a/drivers/dma/edma.c +++ b/drivers/dma/edma.c @@ -113,6 +113,9 @@ #define GET_NUM_REGN(x) ((x & 0x300000) >> 20) /* bits 20-21 */ #define CHMAP_EXIST BIT(24) +/* CCSTAT register */ +#define EDMA_CCSTAT_ACTV BIT(4) + /* * Max of 20 segments per channel to conserve PaRAM slots * Also note that MAX_NR_SG should be atleast the no.of periods @@ -1680,9 +1683,20 @@ static void edma_issue_pending(struct dma_chan *chan) spin_unlock_irqrestore(&echan->vchan.lock, flags); } +/* + * This limit exists to avoid a possible infinite loop when waiting for proof + * that a particular transfer is completed. This limit can be hit if there + * are large bursts to/from slow devices or the CPU is never able to catch + * the DMA hardware idle. On an AM335x transfering 48 bytes from the UART + * RX-FIFO, as many as 55 loops have been seen. + */ +#define EDMA_MAX_TR_WAIT_LOOPS 1000 + static u32 edma_residue(struct edma_desc *edesc) { bool dst = edesc->direction == DMA_DEV_TO_MEM; + int loop_count = EDMA_MAX_TR_WAIT_LOOPS; + struct edma_chan *echan = edesc->echan; struct edma_pset *pset = edesc->pset; dma_addr_t done, pos; int i; @@ -1691,7 +1705,32 @@ static u32 edma_residue(struct edma_desc *edesc) * We always read the dst/src position from the first RamPar * pset. That's the one which is active now. */ - pos = edma_get_position(edesc->echan->ecc, edesc->echan->slot[0], dst); + pos = edma_get_position(echan->ecc, echan->slot[0], dst); + + /* + * "pos" may represent a transfer request that is still being + * processed by the EDMACC or EDMATC. We will busy wait until + * any one of the situations occurs: + * 1. the DMA hardware is idle + * 2. a new transfer request is setup + * 3. we hit the loop limit + */ + while (edma_read(echan->ecc, EDMA_CCSTAT) & EDMA_CCSTAT_ACTV) { + /* check if a new transfer request is setup */ + if (edma_get_position(echan->ecc, + echan->slot[0], dst) != pos) { + break; + } + + if (!--loop_count) { + dev_dbg_ratelimited(echan->vchan.chan.device->dev, + "%s: timeout waiting for PaRAM update\n", + __func__); + break; + } + + cpu_relax(); + } /* * Cyclic is simple. Just subtract pset[0].addr from pos. From ff978b09f973db0d0597704eba350a994d7729e6 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Mon, 8 Feb 2016 00:54:26 -0500 Subject: [PATCH 051/489] ext4 crypto: move context consistency check to ext4_file_open() In the case where the per-file key for the directory is cached, but root does not have access to the key needed to derive the per-file key for the files in the directory, we allow the lookup to succeed, so that lstat(2) and unlink(2) can suceed. However, if a program tries to open the file, it will get an ENOKEY error. Signed-off-by: Theodore Ts'o --- fs/ext4/file.c | 9 +++++++++ fs/ext4/namei.c | 8 ++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 1126436dada1..474f1a4d2ca8 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -350,6 +350,7 @@ static int ext4_file_open(struct inode * inode, struct file * filp) struct super_block *sb = inode->i_sb; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct vfsmount *mnt = filp->f_path.mnt; + struct inode *dir = filp->f_path.dentry->d_parent->d_inode; struct path path; char buf[64], *cp; int ret; @@ -393,6 +394,14 @@ static int ext4_file_open(struct inode * inode, struct file * filp) if (ext4_encryption_info(inode) == NULL) return -ENOKEY; } + if (ext4_encrypted_inode(dir) && + !ext4_is_child_context_consistent_with_parent(dir, inode)) { + ext4_warning(inode->i_sb, + "Inconsistent encryption contexts: %lu/%lu\n", + (unsigned long) dir->i_ino, + (unsigned long) inode->i_ino); + return -EPERM; + } /* * Set up the jbd2_inode if we are opening the inode for * writing and the journal is present diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 5de8483f0062..48e4b8907826 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1603,11 +1603,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi return ERR_PTR(-EFSCORRUPTED); } if (!IS_ERR(inode) && ext4_encrypted_inode(dir) && - (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode)) && + (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) && !ext4_is_child_context_consistent_with_parent(dir, inode)) { + int nokey = ext4_encrypted_inode(inode) && + !ext4_encryption_info(inode); + iput(inode); + if (nokey) + return ERR_PTR(-ENOKEY); ext4_warning(inode->i_sb, "Inconsistent encryption contexts: %lu/%lu\n", (unsigned long) dir->i_ino, From f15838e9cac8f78f0cc506529bb9d3b9fa589c1f Mon Sep 17 00:00:00 2001 From: Andreas Schwab Date: Fri, 5 Feb 2016 19:50:03 +0100 Subject: [PATCH 052/489] powerpc: Fix dedotify for binutils >= 2.26 Since binutils 2.26 BFD is doing suffix merging on STRTAB sections. But dedotify modifies the symbol names in place, which can also modify unrelated symbols with a name that matches a suffix of a dotted name. To remove the leading dot of a symbol name we can just increment the pointer into the STRTAB section instead. Backport to all stables to avoid breakage when people update their binutils - mpe. Cc: stable@vger.kernel.org Signed-off-by: Andreas Schwab Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/module_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c index ac64ffdb52c8..08b7a40de5f8 100644 --- a/arch/powerpc/kernel/module_64.c +++ b/arch/powerpc/kernel/module_64.c @@ -340,7 +340,7 @@ static void dedotify(Elf64_Sym *syms, unsigned int numsyms, char *strtab) if (name[0] == '.') { if (strcmp(name+1, "TOC.") == 0) syms[i].st_shndx = SHN_ABS; - memmove(name, name+1, strlen(name)); + syms[i].st_name++; } } } From c58d6c93680f28ac58984af61d0a7ebf4319c241 Mon Sep 17 00:00:00 2001 From: Phil Turnbull Date: Tue, 2 Feb 2016 13:36:45 -0500 Subject: [PATCH 053/489] netfilter: nfnetlink: correctly validate length of batch messages If nlh->nlmsg_len is zero then an infinite loop is triggered because 'skb_pull(skb, msglen);' pulls zero bytes. The calculation in nlmsg_len() underflows if 'nlh->nlmsg_len < NLMSG_HDRLEN' which bypasses the length validation and will later trigger an out-of-bound read. If the length validation does fail then the malformed batch message is copied back to userspace. However, we cannot do this because the nlh->nlmsg_len can be invalid. This leads to an out-of-bounds read in netlink_ack: [ 41.455421] ================================================================== [ 41.456431] BUG: KASAN: slab-out-of-bounds in memcpy+0x1d/0x40 at addr ffff880119e79340 [ 41.456431] Read of size 4294967280 by task a.out/987 [ 41.456431] ============================================================================= [ 41.456431] BUG kmalloc-512 (Not tainted): kasan: bad access detected [ 41.456431] ----------------------------------------------------------------------------- ... [ 41.456431] Bytes b4 ffff880119e79310: 00 00 00 00 d5 03 00 00 b0 fb fe ff 00 00 00 00 ................ [ 41.456431] Object ffff880119e79320: 20 00 00 00 10 00 05 00 00 00 00 00 00 00 00 00 ............... [ 41.456431] Object ffff880119e79330: 14 00 0a 00 01 03 fc 40 45 56 11 22 33 10 00 05 .......@EV."3... [ 41.456431] Object ffff880119e79340: f0 ff ff ff 88 99 aa bb 00 14 00 0a 00 06 fe fb ................ ^^ start of batch nlmsg with nlmsg_len=4294967280 ... [ 41.456431] Memory state around the buggy address: [ 41.456431] ffff880119e79400: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 41.456431] ffff880119e79480: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 41.456431] >ffff880119e79500: 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc [ 41.456431] ^ [ 41.456431] ffff880119e79580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 41.456431] ffff880119e79600: fc fc fc fc fc fc fc fc fc fc fb fb fb fb fb fb [ 41.456431] ================================================================== Fix this with better validation of nlh->nlmsg_len and by setting NFNL_BATCH_FAILURE if any batch message fails length validation. CAP_NET_ADMIN is required to trigger the bugs. Fixes: 9ea2aa8b7dba ("netfilter: nfnetlink: validate nfnetlink header from batch") Signed-off-by: Phil Turnbull Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nfnetlink.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 62e92af2384a..857ae89633af 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -328,10 +328,12 @@ replay: nlh = nlmsg_hdr(skb); err = 0; - if (nlmsg_len(nlh) < sizeof(struct nfgenmsg) || - skb->len < nlh->nlmsg_len) { - err = -EINVAL; - goto ack; + if (nlh->nlmsg_len < NLMSG_HDRLEN || + skb->len < nlh->nlmsg_len || + nlmsg_len(nlh) < sizeof(struct nfgenmsg)) { + nfnl_err_reset(&err_list); + status |= NFNL_BATCH_FAILURE; + goto done; } /* Only requests are handled by the kernel */ From 08a7f5d3f5c38ed745c3e99ee91975f20562d272 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 5 Feb 2016 10:20:21 +0100 Subject: [PATCH 054/489] netfilter: tee: select NF_DUP_IPV6 unconditionally The NETFILTER_XT_TARGET_TEE option selects NF_DUP_IPV6 whenever IP6_NF_IPTABLES is enabled, and it ensures that it cannot be builtin itself if NF_CONNTRACK is a loadable module, as that is a dependency for NF_DUP_IPV6. However, NF_DUP_IPV6 can be enabled even if IP6_NF_IPTABLES is turned off, and it only really depends on IPV6. With the current check in tee_tg6, we call nf_dup_ipv6() whenever NF_DUP_IPV6 is enabled. This can however be a loadable module which is unreachable from a built-in xt_TEE: net/built-in.o: In function `tee_tg6': :(.text+0x67728): undefined reference to `nf_dup_ipv6' The bug was originally introduced in the split of the xt_TEE module into separate modules for ipv4 and ipv6, and two patches tried to fix it unsuccessfully afterwards. This is a revert of the the first incorrect attempt to fix it, going back to depending on IPV6 as the dependency, and we adapt the 'select' condition accordingly. Signed-off-by: Arnd Bergmann Fixes: bbde9fc1824a ("netfilter: factor out packet duplication for IPv4/IPv6") Fixes: 116984a316c3 ("netfilter: xt_TEE: use IS_ENABLED(CONFIG_NF_DUP_IPV6)") Fixes: 74ec4d55c4d2 ("netfilter: fix xt_TEE and xt_TPROXY dependencies") Signed-off-by: Pablo Neira Ayuso --- net/netfilter/Kconfig | 2 +- net/netfilter/xt_TEE.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 8c067e6663a1..95e757c377f9 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -891,7 +891,7 @@ config NETFILTER_XT_TARGET_TEE depends on IPV6 || IPV6=n depends on !NF_CONNTRACK || NF_CONNTRACK select NF_DUP_IPV4 - select NF_DUP_IPV6 if IP6_NF_IPTABLES != n + select NF_DUP_IPV6 if IPV6 ---help--- This option adds a "TEE" target with which a packet can be cloned and this clone be rerouted to another nexthop. diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c index 3eff7b67cdf2..6e57a3966dc5 100644 --- a/net/netfilter/xt_TEE.c +++ b/net/netfilter/xt_TEE.c @@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -#if IS_ENABLED(CONFIG_NF_DUP_IPV6) +#if IS_ENABLED(CONFIG_IPV6) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { @@ -131,7 +131,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = { .destroy = tee_tg_destroy, .me = THIS_MODULE, }, -#if IS_ENABLED(CONFIG_NF_DUP_IPV6) +#if IS_ENABLED(CONFIG_IPV6) { .name = "TEE", .revision = 1, From 5cc6ce9ff27565949a1001a2889a8dd9fd09e772 Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Sat, 6 Feb 2016 23:31:19 -0500 Subject: [PATCH 055/489] netfilter: nft_counter: fix erroneous return values The nft_counter_init() and nft_counter_clone() functions should return negative error value -ENOMEM instead of positive ENOMEM. Signed-off-by: Anton Protopopov Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_counter.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index c7808fc19719..c9743f78f219 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -100,7 +100,7 @@ static int nft_counter_init(const struct nft_ctx *ctx, cpu_stats = netdev_alloc_pcpu_stats(struct nft_counter_percpu); if (cpu_stats == NULL) - return ENOMEM; + return -ENOMEM; preempt_disable(); this_cpu = this_cpu_ptr(cpu_stats); @@ -138,7 +138,7 @@ static int nft_counter_clone(struct nft_expr *dst, const struct nft_expr *src) cpu_stats = __netdev_alloc_pcpu_stats(struct nft_counter_percpu, GFP_ATOMIC); if (cpu_stats == NULL) - return ENOMEM; + return -ENOMEM; preempt_disable(); this_cpu = this_cpu_ptr(cpu_stats); From f285aa8db7cc4432c1a03f8b55ff34fe96317c11 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 8 Feb 2016 15:30:18 +0100 Subject: [PATCH 056/489] xen/scsiback: correct frontend counting When adding a new frontend to xen-scsiback don't decrement the number of active frontends in case of no error. Doing so results in a failure when trying to remove the xen-pvscsi nexus even if no domain is using it. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Cc: stable@vger.kernel.org Signed-off-by: David Vrabel --- drivers/xen/xen-scsiback.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index ad4eb1024d1f..51387d75c7bf 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -939,12 +939,12 @@ out: spin_unlock_irqrestore(&info->v2p_lock, flags); out_free: - mutex_lock(&tpg->tv_tpg_mutex); - tpg->tv_tpg_fe_count--; - mutex_unlock(&tpg->tv_tpg_mutex); - - if (err) + if (err) { + mutex_lock(&tpg->tv_tpg_mutex); + tpg->tv_tpg_fe_count--; + mutex_unlock(&tpg->tv_tpg_mutex); kfree(new); + } return err; } From c9e2f531be000af652927ee0af3a0f24f8e9e046 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 8 Feb 2016 15:30:19 +0100 Subject: [PATCH 057/489] xen/scsiback: avoid warnings when adding multiple LUNs to a domain When adding more than one LUN to a frontend a warning for a failed assignment is issued in dom0 for each already existing LUN. Avoid this warning by checking for a LUN already existing when existence is allowed (scsiback_do_add_lun() called with try == 1). As the LUN existence check is needed now for a third time, factor it out into a function. This in turn leads to a more or less complete rewrite of scsiback_del_translation_entry() which will now return a proper error code in case of failure. Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel --- drivers/xen/xen-scsiback.c | 70 ++++++++++++++++++++++---------------- 1 file changed, 41 insertions(+), 29 deletions(-) diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c index 51387d75c7bf..c46ee189466f 100644 --- a/drivers/xen/xen-scsiback.c +++ b/drivers/xen/xen-scsiback.c @@ -848,6 +848,24 @@ static int scsiback_map(struct vscsibk_info *info) return scsiback_init_sring(info, ring_ref, evtchn); } +/* + Check for a translation entry being present +*/ +static struct v2p_entry *scsiback_chk_translation_entry( + struct vscsibk_info *info, struct ids_tuple *v) +{ + struct list_head *head = &(info->v2p_entry_lists); + struct v2p_entry *entry; + + list_for_each_entry(entry, head, l) + if ((entry->v.chn == v->chn) && + (entry->v.tgt == v->tgt) && + (entry->v.lun == v->lun)) + return entry; + + return NULL; +} + /* Add a new translation entry */ @@ -855,9 +873,7 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, char *phy, struct ids_tuple *v) { int err = 0; - struct v2p_entry *entry; struct v2p_entry *new; - struct list_head *head = &(info->v2p_entry_lists); unsigned long flags; char *lunp; unsigned long long unpacked_lun; @@ -917,15 +933,10 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, spin_lock_irqsave(&info->v2p_lock, flags); /* Check double assignment to identical virtual ID */ - list_for_each_entry(entry, head, l) { - if ((entry->v.chn == v->chn) && - (entry->v.tgt == v->tgt) && - (entry->v.lun == v->lun)) { - pr_warn("Virtual ID is already used. Assignment was not performed.\n"); - err = -EEXIST; - goto out; - } - + if (scsiback_chk_translation_entry(info, v)) { + pr_warn("Virtual ID is already used. Assignment was not performed.\n"); + err = -EEXIST; + goto out; } /* Create a new translation entry and add to the list */ @@ -933,7 +944,7 @@ static int scsiback_add_translation_entry(struct vscsibk_info *info, new->v = *v; new->tpg = tpg; new->lun = unpacked_lun; - list_add_tail(&new->l, head); + list_add_tail(&new->l, &info->v2p_entry_lists); out: spin_unlock_irqrestore(&info->v2p_lock, flags); @@ -956,39 +967,40 @@ static void __scsiback_del_translation_entry(struct v2p_entry *entry) } /* - Delete the translation entry specfied + Delete the translation entry specified */ static int scsiback_del_translation_entry(struct vscsibk_info *info, struct ids_tuple *v) { struct v2p_entry *entry; - struct list_head *head = &(info->v2p_entry_lists); unsigned long flags; + int ret = 0; spin_lock_irqsave(&info->v2p_lock, flags); /* Find out the translation entry specified */ - list_for_each_entry(entry, head, l) { - if ((entry->v.chn == v->chn) && - (entry->v.tgt == v->tgt) && - (entry->v.lun == v->lun)) { - goto found; - } - } + entry = scsiback_chk_translation_entry(info, v); + if (entry) + __scsiback_del_translation_entry(entry); + else + ret = -ENOENT; spin_unlock_irqrestore(&info->v2p_lock, flags); - return 1; - -found: - /* Delete the translation entry specfied */ - __scsiback_del_translation_entry(entry); - - spin_unlock_irqrestore(&info->v2p_lock, flags); - return 0; + return ret; } static void scsiback_do_add_lun(struct vscsibk_info *info, const char *state, char *phy, struct ids_tuple *vir, int try) { + struct v2p_entry *entry; + unsigned long flags; + + if (try) { + spin_lock_irqsave(&info->v2p_lock, flags); + entry = scsiback_chk_translation_entry(info, vir); + spin_unlock_irqrestore(&info->v2p_lock, flags); + if (entry) + return; + } if (!scsiback_add_translation_entry(info, phy, vir)) { if (xenbus_printf(XBT_NIL, info->dev->nodename, state, "%d", XenbusStateInitialised)) { From 52ba0746b3b44c86aee121babf3b2fd9b8f84090 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Mon, 8 Feb 2016 16:02:06 +0000 Subject: [PATCH 058/489] xen/arm: correctly handle DMA mapping of compound pages Currently xen_dma_map_page concludes that DMA to anything other than the head page of a compound page must be foreign, since the PFN of the page is that of the head. Fix the check to instead consider the whole of a compound page to be local if the PFN of the head passes the 1:1 check. We can never see a compound page which is a mixture of foreign and local sub-pages. The comment already correctly described the intention, but fixup the spelling and some grammar. This fixes the various SSH protocol errors which we have been seeing on the cubietrucks in our automated test infrastructure. This has been broken since commit 3567258d281b ("xen/arm: use hypercall to flush caches in map_page"), which was in v3.19-rc1. NB arch/arm64/.../xen/page-coherent.h also includes this file. Signed-off-by: Ian Campbell Reviewed-by: Stefano Stabellini Cc: xen-devel@lists.xenproject.org Cc: linux-arm-kernel@lists.infradead.org Cc: stable@vger.kernel.org # v3.19+ --- arch/arm/include/asm/xen/page-coherent.h | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 0375c8caa061..9408a994cc91 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -35,14 +35,21 @@ static inline void xen_dma_map_page(struct device *hwdev, struct page *page, dma_addr_t dev_addr, unsigned long offset, size_t size, enum dma_data_direction dir, struct dma_attrs *attrs) { - bool local = XEN_PFN_DOWN(dev_addr) == page_to_xen_pfn(page); + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<map_page(hwdev, page, offset, size, dir, attrs); From 50ab8ec74a153eb30db26529088bc57dd700b24c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 8 Feb 2016 21:11:50 +0100 Subject: [PATCH 059/489] nfs: fix nfs_size_to_loff_t See http: //www.infradead.org/rpr.html X-Evolution-Source: 1451162204.2173.11@leira.trondhjem.org Content-Transfer-Encoding: 8bit Mime-Version: 1.0 We support OFFSET_MAX just fine, so don't round down below it. Also switch to using min_t to make the helper more readable. Signed-off-by: Christoph Hellwig Fixes: 433c92379d9c ("NFS: Clean up nfs_size_to_loff_t()") Cc: stable@vger.kernel.org # 2.6.23+ Signed-off-by: Trond Myklebust --- include/linux/nfs_fs.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 48e0320cd643..67300f8e5f2f 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -550,9 +550,7 @@ extern int nfs_readpage_async(struct nfs_open_context *, struct inode *, static inline loff_t nfs_size_to_loff_t(__u64 size) { - if (size > (__u64) OFFSET_MAX - 1) - return OFFSET_MAX - 1; - return (loff_t) size; + return min_t(u64, size, OFFSET_MAX); } static inline ino_t From 9d021c9d1b4b774a35d8a03d58dbf029544debda Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Sun, 7 Feb 2016 19:34:26 +0100 Subject: [PATCH 060/489] ARM: dts: kirkwood: use unique machine name for ds112 Downstream packages like Debian flash-kernel use /proc/device-tree/model to determine which dtb file to install. Hence each dts in the Linux kernel should provide a unique model identifier. Commit 2d0a7addbd10 ("ARM: Kirkwood: Add support for many Synology NAS devices") created the new files kirkwood-ds111.dts and kirkwood-ds112.dts using the same model identifier. This patch provides a unique model identifier for the Synology DiskStation DS112. Fixes: 2d0a7addbd10 ("ARM: Kirkwood: Add support for many Synology NAS devices") Signed-off-by: Heinrich Schuchardt Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT --- arch/arm/boot/dts/kirkwood-ds112.dts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/kirkwood-ds112.dts b/arch/arm/boot/dts/kirkwood-ds112.dts index bf4143c6cb8f..b84af3da8c84 100644 --- a/arch/arm/boot/dts/kirkwood-ds112.dts +++ b/arch/arm/boot/dts/kirkwood-ds112.dts @@ -14,7 +14,7 @@ #include "kirkwood-synology.dtsi" / { - model = "Synology DS111"; + model = "Synology DS112"; compatible = "synology,ds111", "marvell,kirkwood"; memory { From 44361a2cc13493fc41216d33bb9a562ec3a9cc4e Mon Sep 17 00:00:00 2001 From: Roger Shimizu Date: Sat, 6 Feb 2016 14:59:51 +0900 Subject: [PATCH 061/489] ARM: dts: orion5x: fix the missing mtd flash on linkstation lswtgl MTD flash stores u-boot and u-boot environment on linkstation lswtgl. The latter one can be easily read/write by u-boot-tools package in Debian. Fixes: dc57844a736f ("ARM: dts: orion5x: add buffalo linkstation ls-wtgl") Signed-off-by: Roger Shimizu Reviewed-by: Andrew Lunn Signed-off-by: Gregory CLEMENT --- .../boot/dts/orion5x-linkstation-lswtgl.dts | 31 +++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts index 420788229e6f..aae8a7aceab7 100644 --- a/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts +++ b/arch/arm/boot/dts/orion5x-linkstation-lswtgl.dts @@ -228,6 +228,37 @@ }; }; +&devbus_bootcs { + status = "okay"; + devbus,keep-config; + + flash@0 { + compatible = "jedec-flash"; + reg = <0 0x40000>; + bank-width = <1>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + header@0 { + reg = <0 0x30000>; + read-only; + }; + + uboot@30000 { + reg = <0x30000 0xF000>; + read-only; + }; + + uboot_env@3F000 { + reg = <0x3F000 0x1000>; + }; + }; + }; +}; + &mdio { status = "okay"; From d57d611505d911c6f9f81cd9bd6dbd293d66dd9f Mon Sep 17 00:00:00 2001 From: Stephane Gasparini Date: Tue, 9 Feb 2016 17:07:38 +0100 Subject: [PATCH 062/489] kernel/fs: fix I/O wait not accounted for RW O_DSYNC When a process is doing Random Write with O_DSYNC flag the I/O wait are not accounted in the kernel (get_cpu_iowait_time_us). This is preventing the governor or the cpufreq driver to account for I/O wait and thus use the right pstate Signed-off-by: Stephane Gasparini Signed-off-by: Philippe Longepe Signed-off-by: Jens Axboe --- block/bio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/block/bio.c b/block/bio.c index dbabd48b1934..f53a691b6533 100644 --- a/block/bio.c +++ b/block/bio.c @@ -874,7 +874,7 @@ int submit_bio_wait(int rw, struct bio *bio) bio->bi_private = &ret; bio->bi_end_io = submit_bio_wait_endio; submit_bio(rw, bio); - wait_for_completion(&ret.event); + wait_for_completion_io(&ret.event); return ret.error; } From 21d147880e4895e645f890904784b079f1ba76f4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Tue, 9 Feb 2016 10:21:22 -0700 Subject: [PATCH 063/489] nvme: fix Kconfig description for BLK_DEV_NVME_SCSI Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/Kconfig | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/Kconfig b/drivers/nvme/host/Kconfig index 5d6237391dcd..b586d84f2518 100644 --- a/drivers/nvme/host/Kconfig +++ b/drivers/nvme/host/Kconfig @@ -17,5 +17,6 @@ config BLK_DEV_NVME_SCSI and block devices nodes, as well a a translation for a small number of selected SCSI commands to NVMe commands to the NVMe driver. If you don't know what this means you probably want - to say N here, and if you know what it means you probably - want to say N as well. + to say N here, unless you run a distro that abuses the SCSI + emulation to provide stable device names for mount by id, like + some OpenSuSE and SLES versions. From bcaf669b4bdbad09888df086d266a34e293ace85 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Mon, 8 Feb 2016 09:13:09 -0800 Subject: [PATCH 064/489] arm64: disable kasan when accessing frame->fp in unwind_frame When boot arm64 kernel with KASAN enabled, the below error is reported by kasan: BUG: KASAN: out-of-bounds in unwind_frame+0xec/0x260 at addr ffffffc064d57ba0 Read of size 8 by task pidof/499 page:ffffffbdc39355c0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x0() page dumped because: kasan: bad access detected CPU: 2 PID: 499 Comm: pidof Not tainted 4.5.0-rc1 #119 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [] dump_backtrace+0x0/0x290 [] show_stack+0x24/0x30 [] dump_stack+0x8c/0xd8 [] kasan_report_error+0x558/0x588 [] kasan_report+0x60/0x70 [] __asan_load8+0x60/0x78 [] unwind_frame+0xec/0x260 [] get_wchan+0x110/0x160 [] do_task_stat+0xb44/0xb68 [] proc_tgid_stat+0x40/0x50 [] proc_single_show+0x88/0xd8 [] seq_read+0x370/0x770 [] __vfs_read+0xc8/0x1d8 [] vfs_read+0x94/0x168 [] SyS_read+0xb8/0x128 [] el0_svc_naked+0x24/0x28 Memory state around the buggy address: ffffffc064d57a80: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 00 f4 f4 ffffffc064d57b00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffc064d57b80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffffffc064d57c00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc064d57c80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 Since the shadow byte pointed by the report is 0, so it may mean it is just hit oob in non-current task. So, disable the instrumentation to silence these warnings. Acked-by: Andrey Ryabinin Signed-off-by: Yang Shi Signed-off-by: Will Deacon --- arch/arm64/kernel/stacktrace.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 4fad9787ab46..12a18cbc4295 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -64,8 +64,8 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) return -EINVAL; frame->sp = fp + 0x10; - frame->fp = *(unsigned long *)(fp); - frame->pc = *(unsigned long *)(fp + 8); + frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); + frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); #ifdef CONFIG_FUNCTION_GRAPH_TRACER if (tsk && tsk->ret_stack && From 39a169b62b415390398291080dafe63aec751e0a Mon Sep 17 00:00:00 2001 From: Roman Pen Date: Tue, 9 Feb 2016 12:33:35 -0700 Subject: [PATCH 065/489] block: fix module reference leak on put_disk() call for cgroups throttle get_disk(),get_gendisk() calls have non explicit side effect: they increase the reference on the disk owner module. The following is the correct sequence how to get a disk reference and to put it: disk = get_gendisk(...); /* use disk */ owner = disk->fops->owner; put_disk(disk); module_put(owner); fs/block_dev.c is aware of this required module_put() call, but f.e. blkg_conf_finish(), which is located in block/blk-cgroup.c, does not put a module reference. To see a leakage in action cgroups throttle config can be used. In the following script I'm removing throttle for /dev/ram0 (actually this is NOP, because throttle was never set for this device): # lsmod | grep brd brd 5175 0 # i=100; while [ $i -gt 0 ]; do echo "1:0 0" > \ /sys/fs/cgroup/blkio/blkio.throttle.read_bps_device; i=$(($i - 1)); \ done # lsmod | grep brd brd 5175 100 Now brd module has 100 references. The issue is fixed by calling module_put() just right away put_disk(). Signed-off-by: Roman Pen Cc: Gi-Oh Kim Cc: Tejun Heo Cc: Jens Axboe Cc: linux-block@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5a37188b559f..66e6f1aae02e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -788,6 +788,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, { struct gendisk *disk; struct blkcg_gq *blkg; + struct module *owner; unsigned int major, minor; int key_len, part, ret; char *body; @@ -804,7 +805,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, if (!disk) return -ENODEV; if (part) { + owner = disk->fops->owner; put_disk(disk); + module_put(owner); return -ENODEV; } @@ -820,7 +823,9 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, ret = PTR_ERR(blkg); rcu_read_unlock(); spin_unlock_irq(disk->queue->queue_lock); + owner = disk->fops->owner; put_disk(disk); + module_put(owner); /* * If queue was bypassing, we should retry. Do so after a * short msleep(). It isn't strictly necessary but queue @@ -851,9 +856,13 @@ EXPORT_SYMBOL_GPL(blkg_conf_prep); void blkg_conf_finish(struct blkg_conf_ctx *ctx) __releases(ctx->disk->queue->queue_lock) __releases(rcu) { + struct module *owner; + spin_unlock_irq(ctx->disk->queue->queue_lock); rcu_read_unlock(); + owner = ctx->disk->fops->owner; put_disk(ctx->disk); + module_put(owner); } EXPORT_SYMBOL_GPL(blkg_conf_finish); From fb2d65d28918ef4f0caa1de3d8c7416949c28b41 Mon Sep 17 00:00:00 2001 From: Todd Fujinaka Date: Tue, 9 Feb 2016 21:02:07 -0500 Subject: [PATCH 066/489] SCSI: Add Marvell configuration device to VPD blacklist The Marvell 91xx configuration device also needs to be on the VPD blacklist. [mkp: Match all revisions] Signed-off-by: Todd Fujinaka Signed-off-by: Martin K. Petersen --- drivers/scsi/scsi_devinfo.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/scsi_devinfo.c b/drivers/scsi/scsi_devinfo.c index 820416665324..a63099f2aae4 100644 --- a/drivers/scsi/scsi_devinfo.c +++ b/drivers/scsi/scsi_devinfo.c @@ -206,6 +206,7 @@ static struct { {"iRiver", "iFP Mass Driver", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"LASOUND", "CDX7405", "3.10", BLIST_MAX5LUN | BLIST_SINGLELUN}, {"Marvell", "Console", NULL, BLIST_SKIP_VPD_PAGES}, + {"Marvell", "91xx Config", "1.01", BLIST_SKIP_VPD_PAGES}, {"MATSHITA", "PD-1", NULL, BLIST_FORCELUN | BLIST_SINGLELUN}, {"MATSHITA", "DMC-LC5", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, {"MATSHITA", "DMC-LC40", NULL, BLIST_NOT_LOCKABLE | BLIST_INQUIRY_36}, From 665ca9187c4087736fa57b0e00bcf33ea601fb6f Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sun, 31 Jan 2016 14:23:30 +0100 Subject: [PATCH 067/489] s390/stacktrace: fix save_stack_trace_tsk() for current task The function save_stack_trace_tsk() did not consider that it can be used for tsk == current, for which the current stack pointer obviously cannot be found in the thread structure. Fix this and get the stack pointer with an inline assembly. This fixes e.g. the output of "cat /proc/self/stack". Before: [<0000000000000000>] (null) [] 0xffffffffffffffff After: [<000000000011b3ee>] save_stack_trace_tsk+0x56/0x98 [<0000000000366cde>] proc_pid_stack+0xae/0x108 [<00000000003636f0>] proc_single_show+0x70/0xc0 [<0000000000311fbc>] seq_read+0xcc/0x448 [<00000000002e7716>] __vfs_read+0x36/0x100 [<00000000002e872e>] vfs_read+0x76/0x130 [<00000000002e975e>] SyS_read+0x66/0xd8 [<000000000089490e>] system_call+0xd6/0x264 [] 0xffffffffffffffff Signed-off-by: Heiko Carstens Tested-by: Peter Oberparleiter Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/stacktrace.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 5acba3cb7220..dd484c75be56 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -86,6 +86,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) unsigned long sp, low, high; sp = tsk->thread.ksp; + if (tsk == current) { + /* Get current stack pointer. */ + asm volatile("la %0,0(15)" : "=a" (sp)); + } low = (unsigned long) task_stack_page(tsk); high = (unsigned long) task_pt_regs(tsk); save_context_stack(trace, sp, low, high, 0); From 9900c48c46d8bcf497972024c5fe366e6d9771f3 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 1 Feb 2016 10:13:05 +0100 Subject: [PATCH 068/489] s390/stacktrace: fix address ranges for asynchronous and panic stack git commit dc7ee00d4771 ("s390: lowcore stack pointer offsets") introduced a regression in regard to save_stack_trace(). The stack pointer for the asynchronous and the panic stack in the lowcore now have an additional offset applied to them. This offset needs to be taken into account in the calculation for the low and high address for the stacks. This bug was already partially fixed with 9cc5c206d9b4 ("s390/dumpstack: fix address ranges for asynchronous and panic stack"). This patch fixes it also for the stacktrace code. Fixes: dc7ee00d4771 ("s390: lowcore stack pointer offsets") Signed-off-by: Heiko Carstens Tested-by: Peter Oberparleiter Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/stacktrace.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index dd484c75be56..225bed00aa92 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -62,17 +62,18 @@ static unsigned long save_context_stack(struct stack_trace *trace, void save_stack_trace(struct stack_trace *trace) { register unsigned long sp asm ("15"); - unsigned long orig_sp, new_sp; + unsigned long orig_sp, new_sp, frame_size; + frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); orig_sp = sp; new_sp = save_context_stack(trace, orig_sp, - S390_lowcore.panic_stack - PAGE_SIZE, - S390_lowcore.panic_stack, 1); + S390_lowcore.panic_stack + frame_size - PAGE_SIZE, + S390_lowcore.panic_stack + frame_size, 1); if (new_sp != orig_sp) return; new_sp = save_context_stack(trace, new_sp, - S390_lowcore.async_stack - ASYNC_SIZE, - S390_lowcore.async_stack, 1); + S390_lowcore.async_stack + frame_size - ASYNC_SIZE, + S390_lowcore.async_stack + frame_size, 1); if (new_sp != orig_sp) return; save_context_stack(trace, new_sp, From f6331aaccbd980a49bff1559d66abcbd46af5b0a Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 1 Feb 2016 14:06:57 +0100 Subject: [PATCH 069/489] s390/stacktrace: add missing end marker save_stack_trace() did not write the ULONG_MAX end marker if there is enough space left. So simply follow x86 and arm64. Signed-off-by: Heiko Carstens Tested-by: Peter Oberparleiter Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/stacktrace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 225bed00aa92..75e6ea930692 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -79,6 +79,8 @@ void save_stack_trace(struct stack_trace *trace) save_context_stack(trace, new_sp, S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE, 1); + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace); From 66adce8f1f9f3bcd743a0e72c10aa850df8c5fa7 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 1 Feb 2016 14:14:04 +0100 Subject: [PATCH 070/489] s390/stacktrace: save full stack traces save_stack_trace() only saves the stack trace of the current context (interrupt or process context). This is different to what other architectures like x86 do, which save the full stack trace across different contexts. Also extract a __save_stack_trace() helper function which will be used by a follow on patch. Signed-off-by: Heiko Carstens Tested-by: Peter Oberparleiter Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/stacktrace.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index 75e6ea930692..e0fec2d8ac40 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -59,26 +59,29 @@ static unsigned long save_context_stack(struct stack_trace *trace, } } -void save_stack_trace(struct stack_trace *trace) +static void __save_stack_trace(struct stack_trace *trace, unsigned long sp) { - register unsigned long sp asm ("15"); - unsigned long orig_sp, new_sp, frame_size; + unsigned long new_sp, frame_size; frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); - orig_sp = sp; - new_sp = save_context_stack(trace, orig_sp, + new_sp = save_context_stack(trace, sp, S390_lowcore.panic_stack + frame_size - PAGE_SIZE, S390_lowcore.panic_stack + frame_size, 1); - if (new_sp != orig_sp) - return; new_sp = save_context_stack(trace, new_sp, S390_lowcore.async_stack + frame_size - ASYNC_SIZE, S390_lowcore.async_stack + frame_size, 1); - if (new_sp != orig_sp) - return; save_context_stack(trace, new_sp, S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE, 1); +} + +void save_stack_trace(struct stack_trace *trace) +{ + register unsigned long r15 asm ("15"); + unsigned long sp; + + sp = r15; + __save_stack_trace(trace, sp); if (trace->nr_entries < trace->max_entries) trace->entries[trace->nr_entries++] = ULONG_MAX; } From e0115875c04548255212ebd7dbd90bdbe1257f48 Mon Sep 17 00:00:00 2001 From: Pratyush Anand Date: Fri, 29 Jan 2016 10:50:28 +0530 Subject: [PATCH 071/489] s390/stacktrace: add save_stack_trace_regs() Implement save_stack_trace_regs, so that a stack trace of a kprobe event can be obtained. Without this we see following warning: "save_stack_trace_regs() not implemented yet." when we execute: echo stacktrace > /sys/kernel/debug/tracing/trace_options echo "p kfree" >> /sys/kernel/debug/tracing/kprobe_events echo 1 > /sys/kernel/debug/tracing/events/kprobes/enable Reported-by: Chunyu Hu Signed-off-by: Pratyush Anand [heiko.carstens@de.ibm.com]: changed patch to use __save_stack_trace() Signed-off-by: Heiko Carstens Tested-by: Peter Oberparleiter Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/stacktrace.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c index e0fec2d8ac40..8f64ebd63767 100644 --- a/arch/s390/kernel/stacktrace.c +++ b/arch/s390/kernel/stacktrace.c @@ -103,3 +103,14 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) trace->entries[trace->nr_entries++] = ULONG_MAX; } EXPORT_SYMBOL_GPL(save_stack_trace_tsk); + +void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + unsigned long sp; + + sp = kernel_stack_pointer(regs); + __save_stack_trace(trace, sp); + if (trace->nr_entries < trace->max_entries) + trace->entries[trace->nr_entries++] = ULONG_MAX; +} +EXPORT_SYMBOL_GPL(save_stack_trace_regs); From 1f8cbb9c8365061d8b866e9b4f4403e029d57989 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 9 Feb 2016 12:00:16 +0100 Subject: [PATCH 072/489] s390/perf_event: fix address range for asynchronous stack git commit dc7ee00d4771 ("s390: lowcore stack pointer offsets") introduced a regression in regard to perf_callchain_kernel(). The stack pointer for the asynchronous stack in the lowcore now has an additional offset applied. This offset needs to be taken into account in the calculation for the low and high address for the stack. This bug was already partially fixed with 9cc5c206d9b4 ("s390/dumpstack: fix address ranges for asynchronous and panic stack"). This patch fixes it also for the perf_event code. Fixes: dc7ee00d4771 ("s390: lowcore stack pointer offsets") Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/perf_event.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c index cfcba2dd9bb5..0943b11a2f6e 100644 --- a/arch/s390/kernel/perf_event.c +++ b/arch/s390/kernel/perf_event.c @@ -260,12 +260,13 @@ static unsigned long __store_trace(struct perf_callchain_entry *entry, void perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs) { - unsigned long head; + unsigned long head, frame_size; struct stack_frame *head_sf; if (user_mode(regs)) return; + frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); head = regs->gprs[15]; head_sf = (struct stack_frame *) head; @@ -273,8 +274,9 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry, return; head = head_sf->back_chain; - head = __store_trace(entry, head, S390_lowcore.async_stack - ASYNC_SIZE, - S390_lowcore.async_stack); + head = __store_trace(entry, head, + S390_lowcore.async_stack + frame_size - ASYNC_SIZE, + S390_lowcore.async_stack + frame_size); __store_trace(entry, head, S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE); From 232f5dd78586a684a7364a486b934e19384189dc Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Tue, 9 Feb 2016 12:03:31 +0100 Subject: [PATCH 073/489] s390/oprofile: fix address range for asynchronous stack git commit dc7ee00d4771 ("s390: lowcore stack pointer offsets") introduced a regression in regard to s390_backtrace(). The stack pointer for the asynchronous stack in the lowcore now has an additional offset applied. This offset needs to be taken into account in the calculation for the low and high address for the stack. This bug was already partially fixed with commit 9cc5c206d9b4 ("s390/dumpstack: fix address ranges for asynchronous and panic stack"). This patch fixes it also for the oprofile code. Fixes: dc7ee00d4771 ("s390: lowcore stack pointer offsets") Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/oprofile/backtrace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c index fe0bfe370c45..1884e1759529 100644 --- a/arch/s390/oprofile/backtrace.c +++ b/arch/s390/oprofile/backtrace.c @@ -54,12 +54,13 @@ __show_trace(unsigned int *depth, unsigned long sp, void s390_backtrace(struct pt_regs * const regs, unsigned int depth) { - unsigned long head; + unsigned long head, frame_size; struct stack_frame* head_sf; if (user_mode(regs)) return; + frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); head = regs->gprs[15]; head_sf = (struct stack_frame*)head; @@ -68,8 +69,9 @@ void s390_backtrace(struct pt_regs * const regs, unsigned int depth) head = head_sf->back_chain; - head = __show_trace(&depth, head, S390_lowcore.async_stack - ASYNC_SIZE, - S390_lowcore.async_stack); + head = __show_trace(&depth, head, + S390_lowcore.async_stack + frame_size - ASYNC_SIZE, + S390_lowcore.async_stack + frame_size); __show_trace(&depth, head, S390_lowcore.thread_info, S390_lowcore.thread_info + THREAD_SIZE); From 73500267c930baadadb0d02284909731baf151f7 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:11 -0500 Subject: [PATCH 074/489] lib/ucs2_string: Add ucs2 -> utf8 helper functions This adds ucs2_utf8size(), which tells us how big our ucs2 string is in bytes, and ucs2_as_utf8, which translates from ucs2 to utf8.. Signed-off-by: Peter Jones Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- include/linux/ucs2_string.h | 4 +++ lib/ucs2_string.c | 62 +++++++++++++++++++++++++++++++++++++ 2 files changed, 66 insertions(+) diff --git a/include/linux/ucs2_string.h b/include/linux/ucs2_string.h index cbb20afdbc01..bb679b48f408 100644 --- a/include/linux/ucs2_string.h +++ b/include/linux/ucs2_string.h @@ -11,4 +11,8 @@ unsigned long ucs2_strlen(const ucs2_char_t *s); unsigned long ucs2_strsize(const ucs2_char_t *data, unsigned long maxlength); int ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len); +unsigned long ucs2_utf8size(const ucs2_char_t *src); +unsigned long ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, + unsigned long maxlength); + #endif /* _LINUX_UCS2_STRING_H_ */ diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 6f500ef2301d..17dd74e21ef9 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -49,3 +49,65 @@ ucs2_strncmp(const ucs2_char_t *a, const ucs2_char_t *b, size_t len) } } EXPORT_SYMBOL(ucs2_strncmp); + +unsigned long +ucs2_utf8size(const ucs2_char_t *src) +{ + unsigned long i; + unsigned long j = 0; + + for (i = 0; i < ucs2_strlen(src); i++) { + u16 c = src[i]; + + if (c > 0x800) + j += 3; + else if (c > 0x80) + j += 2; + else + j += 1; + } + + return j; +} +EXPORT_SYMBOL(ucs2_utf8size); + +/* + * copy at most maxlength bytes of whole utf8 characters to dest from the + * ucs2 string src. + * + * The return value is the number of characters copied, not including the + * final NUL character. + */ +unsigned long +ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength) +{ + unsigned int i; + unsigned long j = 0; + unsigned long limit = ucs2_strnlen(src, maxlength); + + for (i = 0; maxlength && i < limit; i++) { + u16 c = src[i]; + + if (c > 0x800) { + if (maxlength < 3) + break; + maxlength -= 3; + dest[j++] = 0xe0 | (c & 0xf000) >> 12; + dest[j++] = 0x80 | (c & 0x0fc0) >> 8; + dest[j++] = 0x80 | (c & 0x003f); + } else if (c > 0x80) { + if (maxlength < 2) + break; + maxlength -= 2; + dest[j++] = 0xc0 | (c & 0xfe0) >> 5; + dest[j++] = 0x80 | (c & 0x01f); + } else { + maxlength -= 1; + dest[j++] = c & 0x7f; + } + } + if (maxlength) + dest[j] = '\0'; + return j; +} +EXPORT_SYMBOL(ucs2_as_utf8); From e0d64e6a880e64545ad7d55786aa84ab76bac475 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:12 -0500 Subject: [PATCH 075/489] efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version Translate EFI's UCS-2 variable names to UTF-8 instead of just assuming all variable names fit in ASCII. Signed-off-by: Peter Jones Acked-by: Matthew Garrett Tested-by: Lee, Chun-Yi Signed-off-by: Matt Fleming --- drivers/firmware/efi/efivars.c | 30 +++++++++++------------------- fs/efivarfs/super.c | 7 +++---- 2 files changed, 14 insertions(+), 23 deletions(-) diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index 756eca8c4cf8..f4ff8abc5f3e 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -540,38 +540,30 @@ static ssize_t efivar_delete(struct file *filp, struct kobject *kobj, static int efivar_create_sysfs_entry(struct efivar_entry *new_var) { - int i, short_name_size; + int short_name_size; char *short_name; - unsigned long variable_name_size; - efi_char16_t *variable_name; + unsigned long utf8_name_size; + efi_char16_t *variable_name = new_var->var.VariableName; int ret; - variable_name = new_var->var.VariableName; - variable_name_size = ucs2_strlen(variable_name) * sizeof(efi_char16_t); - /* - * Length of the variable bytes in ASCII, plus the '-' separator, + * Length of the variable bytes in UTF8, plus the '-' separator, * plus the GUID, plus trailing NUL */ - short_name_size = variable_name_size / sizeof(efi_char16_t) - + 1 + EFI_VARIABLE_GUID_LEN + 1; - - short_name = kzalloc(short_name_size, GFP_KERNEL); + utf8_name_size = ucs2_utf8size(variable_name); + short_name_size = utf8_name_size + 1 + EFI_VARIABLE_GUID_LEN + 1; + short_name = kmalloc(short_name_size, GFP_KERNEL); if (!short_name) return -ENOMEM; - /* Convert Unicode to normal chars (assume top bits are 0), - ala UTF-8 */ - for (i=0; i < (int)(variable_name_size / sizeof(efi_char16_t)); i++) { - short_name[i] = variable_name[i] & 0xFF; - } + ucs2_as_utf8(short_name, variable_name, short_name_size); + /* This is ugly, but necessary to separate one vendor's private variables from another's. */ - - *(short_name + strlen(short_name)) = '-'; + short_name[utf8_name_size] = '-'; efi_guid_to_str(&new_var->var.VendorGuid, - short_name + strlen(short_name)); + short_name + utf8_name_size + 1); new_var->kobj.kset = efivars_kset; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index b8a564f29107..8651ac28ec0d 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -118,7 +118,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, struct dentry *dentry, *root = sb->s_root; unsigned long size = 0; char *name; - int len, i; + int len; int err = -ENOMEM; entry = kzalloc(sizeof(*entry), GFP_KERNEL); @@ -128,15 +128,14 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, memcpy(entry->var.VariableName, name16, name_size); memcpy(&(entry->var.VendorGuid), &vendor, sizeof(efi_guid_t)); - len = ucs2_strlen(entry->var.VariableName); + len = ucs2_utf8size(entry->var.VariableName); /* name, plus '-', plus GUID, plus NUL*/ name = kmalloc(len + 1 + EFI_VARIABLE_GUID_LEN + 1, GFP_KERNEL); if (!name) goto fail; - for (i = 0; i < len; i++) - name[i] = entry->var.VariableName[i] & 0xFF; + ucs2_as_utf8(name, entry->var.VariableName, len); name[len] = '-'; From 3dcb1f55dfc7631695e69df4a0d589ce5274bd07 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:13 -0500 Subject: [PATCH 076/489] efi: Do variable name validation tests in utf8 Actually translate from ucs2 to utf8 before doing the test, and then test against our other utf8 data, instead of fudging it. Signed-off-by: Peter Jones Acked-by: Matthew Garrett Tested-by: Lee, Chun-Yi Signed-off-by: Matt Fleming --- drivers/firmware/efi/vars.c | 32 +++++++++++++++++++++----------- 1 file changed, 21 insertions(+), 11 deletions(-) diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 70a0fb10517f..5c5fde3e6c37 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -189,10 +189,19 @@ static const struct variable_validate variable_validate[] = { }; bool -efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len) +efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size) { int i; - u16 *unicode_name = var_name; + unsigned long utf8_size; + u8 *utf8_name; + + utf8_size = ucs2_utf8size(var_name); + utf8_name = kmalloc(utf8_size + 1, GFP_KERNEL); + if (!utf8_name) + return false; + + ucs2_as_utf8(utf8_name, var_name, utf8_size); + utf8_name[utf8_size] = '\0'; for (i = 0; variable_validate[i].validate != NULL; i++) { const char *name = variable_validate[i].name; @@ -200,28 +209,29 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len) for (match = 0; ; match++) { char c = name[match]; - u16 u = unicode_name[match]; - - /* All special variables are plain ascii */ - if (u > 127) - return true; + char u = utf8_name[match]; /* Wildcard in the matching name means we've matched */ - if (c == '*') + if (c == '*') { + kfree(utf8_name); return variable_validate[i].validate(var_name, - match, data, len); + match, data, data_size); + } /* Case sensitive match */ if (c != u) break; /* Reached the end of the string while matching */ - if (!c) + if (!c) { + kfree(utf8_name); return variable_validate[i].validate(var_name, - match, data, len); + match, data, data_size); + } } } + kfree(utf8_name); return true; } EXPORT_SYMBOL_GPL(efivar_validate); From e04a28d45ff343b47a4ffc4dee3a3e279e76ddfa Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 10 Feb 2016 16:05:28 +0000 Subject: [PATCH 077/489] arm64: debug: re-enable irqs before sending breakpoint SIGTRAP force_sig_info can sleep under an -rt kernel, so attempting to send a breakpoint SIGTRAP with interrupts disabled yields the following BUG: BUG: sleeping function called from invalid context at /kernel-source/kernel/locking/rtmutex.c:917 in_atomic(): 0, irqs_disabled(): 128, pid: 551, name: test.sh CPU: 5 PID: 551 Comm: test.sh Not tainted 4.1.13-rt13 #7 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: dump_backtrace+0x0/0x128 show_stack+0x24/0x30 dump_stack+0x80/0xa0 ___might_sleep+0x128/0x1a0 rt_spin_lock+0x2c/0x40 force_sig_info+0xcc/0x210 brk_handler.part.2+0x6c/0x80 brk_handler+0xd8/0xe8 do_debug_exception+0x58/0xb8 This patch fixes the problem by ensuring that interrupts are enabled prior to sending the SIGTRAP if they were already enabled in the user context. Reported-by: Yang Shi Signed-off-by: Will Deacon --- arch/arm64/kernel/debug-monitors.c | 48 ++++++++++++++---------------- 1 file changed, 22 insertions(+), 26 deletions(-) diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 8aee3aeec3e6..c536c9e307b9 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -226,11 +226,28 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) return retval; } +static void send_user_sigtrap(int si_code) +{ + struct pt_regs *regs = current_pt_regs(); + siginfo_t info = { + .si_signo = SIGTRAP, + .si_errno = 0, + .si_code = si_code, + .si_addr = (void __user *)instruction_pointer(regs), + }; + + if (WARN_ON(!user_mode(regs))) + return; + + if (interrupts_enabled(regs)) + local_irq_enable(); + + force_sig_info(SIGTRAP, &info, current); +} + static int single_step_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - siginfo_t info; - /* * If we are stepping a pending breakpoint, call the hw_breakpoint * handler first. @@ -239,11 +256,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr, return 0; if (user_mode(regs)) { - info.si_signo = SIGTRAP; - info.si_errno = 0; - info.si_code = TRAP_HWBKPT; - info.si_addr = (void __user *)instruction_pointer(regs); - force_sig_info(SIGTRAP, &info, current); + send_user_sigtrap(TRAP_HWBKPT); /* * ptrace will disable single step unless explicitly @@ -307,17 +320,8 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) static int brk_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { - siginfo_t info; - if (user_mode(regs)) { - info = (siginfo_t) { - .si_signo = SIGTRAP, - .si_errno = 0, - .si_code = TRAP_BRKPT, - .si_addr = (void __user *)instruction_pointer(regs), - }; - - force_sig_info(SIGTRAP, &info, current); + send_user_sigtrap(TRAP_BRKPT); } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) { pr_warning("Unexpected kernel BRK exception at EL1\n"); return -EFAULT; @@ -328,7 +332,6 @@ static int brk_handler(unsigned long addr, unsigned int esr, int aarch32_break_handler(struct pt_regs *regs) { - siginfo_t info; u32 arm_instr; u16 thumb_instr; bool bp = false; @@ -359,14 +362,7 @@ int aarch32_break_handler(struct pt_regs *regs) if (!bp) return -EFAULT; - info = (siginfo_t) { - .si_signo = SIGTRAP, - .si_errno = 0, - .si_code = TRAP_BRKPT, - .si_addr = pc, - }; - - force_sig_info(SIGTRAP, &info, current); + send_user_sigtrap(TRAP_BRKPT); return 0; } From 0ad4ece5bbd4d2104564c7dbd477ae0c729d4fcc Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 10 Feb 2016 18:13:30 +0200 Subject: [PATCH 078/489] iwlwifi: dvm: remove a wrong dependency on m This was wronly added when the dependency on IWLWIFI was removed. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=112201 Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/intel/iwlwifi/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig index 866067789330..7438fbeef744 100644 --- a/drivers/net/wireless/intel/iwlwifi/Kconfig +++ b/drivers/net/wireless/intel/iwlwifi/Kconfig @@ -53,7 +53,6 @@ config IWLWIFI_LEDS config IWLDVM tristate "Intel Wireless WiFi DVM Firmware support" - depends on m help This is the driver that supports the DVM firmware. The list of the devices that use this firmware is available here: From 8282f5d9c17fe15a9e658c06e3f343efae1a2a2f Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:14 -0500 Subject: [PATCH 079/489] efi: Make our variable validation list include the guid All the variables in this list so far are defined to be in the global namespace in the UEFI spec, so this just further ensures we're validating the variables we think we are. Including the guid for entries will become more important in future patches when we decide whether or not to allow deletion of variables based on presence in this list. Signed-off-by: Peter Jones Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- drivers/firmware/efi/efivars.c | 5 ++-- drivers/firmware/efi/vars.c | 52 +++++++++++++++++++++------------- include/linux/efi.h | 3 +- 3 files changed, 38 insertions(+), 22 deletions(-) diff --git a/drivers/firmware/efi/efivars.c b/drivers/firmware/efi/efivars.c index f4ff8abc5f3e..10e6774ab2a2 100644 --- a/drivers/firmware/efi/efivars.c +++ b/drivers/firmware/efi/efivars.c @@ -221,7 +221,7 @@ sanity_check(struct efi_variable *var, efi_char16_t *name, efi_guid_t vendor, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(vendor, name, data, size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } @@ -447,7 +447,8 @@ static ssize_t efivar_create(struct file *filp, struct kobject *kobj, } if ((attributes & ~EFI_VARIABLE_MASK) != 0 || - efivar_validate(name, data, size) == false) { + efivar_validate(new_var->VendorGuid, name, data, + size) == false) { printk(KERN_ERR "efivars: Malformed variable content\n"); return -EINVAL; } diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 5c5fde3e6c37..9a53da21e7b6 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -165,31 +165,42 @@ validate_ascii_string(efi_char16_t *var_name, int match, u8 *buffer, } struct variable_validate { + efi_guid_t vendor; char *name; bool (*validate)(efi_char16_t *var_name, int match, u8 *data, unsigned long len); }; +/* + * This is the list of variables we need to validate. + * + * If it has a validate() method that's not NULL, it'll go into the + * validation routine. If not, it is assumed valid. + * + * Note that it's sorted by {vendor,name}, but globbed names must come after + * any other name with the same prefix. + */ static const struct variable_validate variable_validate[] = { - { "BootNext", validate_uint16 }, - { "BootOrder", validate_boot_order }, - { "DriverOrder", validate_boot_order }, - { "Boot*", validate_load_option }, - { "Driver*", validate_load_option }, - { "ConIn", validate_device_path }, - { "ConInDev", validate_device_path }, - { "ConOut", validate_device_path }, - { "ConOutDev", validate_device_path }, - { "ErrOut", validate_device_path }, - { "ErrOutDev", validate_device_path }, - { "Timeout", validate_uint16 }, - { "Lang", validate_ascii_string }, - { "PlatformLang", validate_ascii_string }, - { "", NULL }, + { EFI_GLOBAL_VARIABLE_GUID, "BootNext", validate_uint16 }, + { EFI_GLOBAL_VARIABLE_GUID, "BootOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Boot*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "DriverOrder", validate_boot_order }, + { EFI_GLOBAL_VARIABLE_GUID, "Driver*", validate_load_option }, + { EFI_GLOBAL_VARIABLE_GUID, "ConIn", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConInDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ConOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path }, + { EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, + { NULL_GUID, "", NULL }, }; bool -efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size) +efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size) { int i; unsigned long utf8_size; @@ -203,9 +214,12 @@ efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long data_size) ucs2_as_utf8(utf8_name, var_name, utf8_size); utf8_name[utf8_size] = '\0'; - for (i = 0; variable_validate[i].validate != NULL; i++) { + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { const char *name = variable_validate[i].name; - int match; + int match = 0; + + if (efi_guidcmp(vendor, variable_validate[i].vendor)) + continue; for (match = 0; ; match++) { char c = name[match]; @@ -862,7 +876,7 @@ int efivar_entry_set_get_size(struct efivar_entry *entry, u32 attributes, *set = false; - if (efivar_validate(name, data, *size) == false) + if (efivar_validate(*vendor, name, data, *size) == false) return -EINVAL; /* diff --git a/include/linux/efi.h b/include/linux/efi.h index 569b5a866bb1..16ca611aabc8 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1199,7 +1199,8 @@ int efivar_entry_iter(int (*func)(struct efivar_entry *, void *), struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, struct list_head *head, bool remove); -bool efivar_validate(efi_char16_t *var_name, u8 *data, unsigned long len); +bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, + unsigned long data_size); extern struct work_struct efivar_work; void efivar_run_worker(void); From ed8b0de5a33d2a2557dce7f9429dca8cb5bc5879 Mon Sep 17 00:00:00 2001 From: Peter Jones Date: Mon, 8 Feb 2016 14:48:15 -0500 Subject: [PATCH 080/489] efi: Make efivarfs entries immutable by default "rm -rf" is bricking some peoples' laptops because of variables being used to store non-reinitializable firmware driver data that's required to POST the hardware. These are 100% bugs, and they need to be fixed, but in the mean time it shouldn't be easy to *accidentally* brick machines. We have to have delete working, and picking which variables do and don't work for deletion is quite intractable, so instead make everything immutable by default (except for a whitelist), and make tools that aren't quite so broad-spectrum unset the immutable flag. Signed-off-by: Peter Jones Tested-by: Lee, Chun-Yi Acked-by: Matthew Garrett Signed-off-by: Matt Fleming --- Documentation/filesystems/efivarfs.txt | 7 ++ drivers/firmware/efi/vars.c | 87 ++++++++++++++----- fs/efivarfs/file.c | 70 +++++++++++++++ fs/efivarfs/inode.c | 30 ++++--- fs/efivarfs/internal.h | 3 +- fs/efivarfs/super.c | 9 +- include/linux/efi.h | 2 + tools/testing/selftests/efivarfs/efivarfs.sh | 19 +++- .../testing/selftests/efivarfs/open-unlink.c | 72 ++++++++++++++- 9 files changed, 258 insertions(+), 41 deletions(-) diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt index c477af086e65..686a64bba775 100644 --- a/Documentation/filesystems/efivarfs.txt +++ b/Documentation/filesystems/efivarfs.txt @@ -14,3 +14,10 @@ filesystem. efivarfs is typically mounted like this, mount -t efivarfs none /sys/firmware/efi/efivars + +Due to the presence of numerous firmware bugs where removing non-standard +UEFI variables causes the system firmware to fail to POST, efivarfs +files that are not well-known standardized variables are created +as immutable files. This doesn't prevent removal - "chattr -i" will work - +but it does prevent this kind of failure from being accomplished +accidentally. diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 9a53da21e7b6..50f10bad2604 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -172,10 +172,12 @@ struct variable_validate { }; /* - * This is the list of variables we need to validate. + * This is the list of variables we need to validate, as well as the + * whitelist for what we think is safe not to default to immutable. * * If it has a validate() method that's not NULL, it'll go into the - * validation routine. If not, it is assumed valid. + * validation routine. If not, it is assumed valid, but still used for + * whitelisting. * * Note that it's sorted by {vendor,name}, but globbed names must come after * any other name with the same prefix. @@ -193,11 +195,37 @@ static const struct variable_validate variable_validate[] = { { EFI_GLOBAL_VARIABLE_GUID, "ErrOut", validate_device_path }, { EFI_GLOBAL_VARIABLE_GUID, "ErrOutDev", validate_device_path }, { EFI_GLOBAL_VARIABLE_GUID, "Lang", validate_ascii_string }, + { EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL }, { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, { NULL_GUID, "", NULL }, }; +static bool +variable_matches(const char *var_name, size_t len, const char *match_name, + int *match) +{ + for (*match = 0; ; (*match)++) { + char c = match_name[*match]; + char u = var_name[*match]; + + /* Wildcard in the matching name means we've matched */ + if (c == '*') + return true; + + /* Case sensitive match */ + if (!c && *match == len) + return true; + + if (c != u) + return false; + + if (!c) + return true; + } + return true; +} + bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, unsigned long data_size) @@ -221,35 +249,48 @@ efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, if (efi_guidcmp(vendor, variable_validate[i].vendor)) continue; - for (match = 0; ; match++) { - char c = name[match]; - char u = utf8_name[match]; - - /* Wildcard in the matching name means we've matched */ - if (c == '*') { - kfree(utf8_name); - return variable_validate[i].validate(var_name, - match, data, data_size); - } - - /* Case sensitive match */ - if (c != u) + if (variable_matches(utf8_name, utf8_size+1, name, &match)) { + if (variable_validate[i].validate == NULL) break; - - /* Reached the end of the string while matching */ - if (!c) { - kfree(utf8_name); - return variable_validate[i].validate(var_name, - match, data, data_size); - } + kfree(utf8_name); + return variable_validate[i].validate(var_name, match, + data, data_size); } } - kfree(utf8_name); return true; } EXPORT_SYMBOL_GPL(efivar_validate); +bool +efivar_variable_is_removable(efi_guid_t vendor, const char *var_name, + size_t len) +{ + int i; + bool found = false; + int match = 0; + + /* + * Check if our variable is in the validated variables list + */ + for (i = 0; variable_validate[i].name[0] != '\0'; i++) { + if (efi_guidcmp(variable_validate[i].vendor, vendor)) + continue; + + if (variable_matches(var_name, len, + variable_validate[i].name, &match)) { + found = true; + break; + } + } + + /* + * If it's in our list, it is removable. + */ + return found; +} +EXPORT_SYMBOL_GPL(efivar_variable_is_removable); + static efi_status_t check_var_size(u32 attributes, unsigned long size) { diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c index c424e4813ec8..d48e0d261d78 100644 --- a/fs/efivarfs/file.c +++ b/fs/efivarfs/file.c @@ -10,6 +10,7 @@ #include #include #include +#include #include "internal.h" @@ -103,9 +104,78 @@ out_free: return size; } +static int +efivarfs_ioc_getxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int i_flags; + unsigned int flags = 0; + + i_flags = inode->i_flags; + if (i_flags & S_IMMUTABLE) + flags |= FS_IMMUTABLE_FL; + + if (copy_to_user(arg, &flags, sizeof(flags))) + return -EFAULT; + return 0; +} + +static int +efivarfs_ioc_setxflags(struct file *file, void __user *arg) +{ + struct inode *inode = file->f_mapping->host; + unsigned int flags; + unsigned int i_flags = 0; + int error; + + if (!inode_owner_or_capable(inode)) + return -EACCES; + + if (copy_from_user(&flags, arg, sizeof(flags))) + return -EFAULT; + + if (flags & ~FS_IMMUTABLE_FL) + return -EOPNOTSUPP; + + if (!capable(CAP_LINUX_IMMUTABLE)) + return -EPERM; + + if (flags & FS_IMMUTABLE_FL) + i_flags |= S_IMMUTABLE; + + + error = mnt_want_write_file(file); + if (error) + return error; + + inode_lock(inode); + inode_set_flags(inode, i_flags, S_IMMUTABLE); + inode_unlock(inode); + + mnt_drop_write_file(file); + + return 0; +} + +long +efivarfs_file_ioctl(struct file *file, unsigned int cmd, unsigned long p) +{ + void __user *arg = (void __user *)p; + + switch (cmd) { + case FS_IOC_GETFLAGS: + return efivarfs_ioc_getxflags(file, arg); + case FS_IOC_SETFLAGS: + return efivarfs_ioc_setxflags(file, arg); + } + + return -ENOTTY; +} + const struct file_operations efivarfs_file_operations = { .open = simple_open, .read = efivarfs_file_read, .write = efivarfs_file_write, .llseek = no_llseek, + .unlocked_ioctl = efivarfs_file_ioctl, }; diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c index 3381b9da9ee6..e2ab6d0497f2 100644 --- a/fs/efivarfs/inode.c +++ b/fs/efivarfs/inode.c @@ -15,7 +15,8 @@ #include "internal.h" struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev) + const struct inode *dir, int mode, + dev_t dev, bool is_removable) { struct inode *inode = new_inode(sb); @@ -23,6 +24,7 @@ struct inode *efivarfs_get_inode(struct super_block *sb, inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_flags = is_removable ? 0 : S_IMMUTABLE; switch (mode & S_IFMT) { case S_IFREG: inode->i_fop = &efivarfs_file_operations; @@ -102,22 +104,17 @@ static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) static int efivarfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { - struct inode *inode; + struct inode *inode = NULL; struct efivar_entry *var; int namelen, i = 0, err = 0; + bool is_removable = false; if (!efivarfs_valid_name(dentry->d_name.name, dentry->d_name.len)) return -EINVAL; - inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); - if (!inode) - return -ENOMEM; - var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); - if (!var) { - err = -ENOMEM; - goto out; - } + if (!var) + return -ENOMEM; /* length of the variable name itself: remove GUID and separator */ namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1; @@ -125,6 +122,16 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, &var->var.VendorGuid); + if (efivar_variable_is_removable(var->var.VendorGuid, + dentry->d_name.name, namelen)) + is_removable = true; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0, is_removable); + if (!inode) { + err = -ENOMEM; + goto out; + } + for (i = 0; i < namelen; i++) var->var.VariableName[i] = dentry->d_name.name[i]; @@ -138,7 +145,8 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry, out: if (err) { kfree(var); - iput(inode); + if (inode) + iput(inode); } return err; } diff --git a/fs/efivarfs/internal.h b/fs/efivarfs/internal.h index b5ff16addb7c..b4505188e799 100644 --- a/fs/efivarfs/internal.h +++ b/fs/efivarfs/internal.h @@ -15,7 +15,8 @@ extern const struct file_operations efivarfs_file_operations; extern const struct inode_operations efivarfs_dir_inode_operations; extern bool efivarfs_valid_name(const char *str, int len); extern struct inode *efivarfs_get_inode(struct super_block *sb, - const struct inode *dir, int mode, dev_t dev); + const struct inode *dir, int mode, dev_t dev, + bool is_removable); extern struct list_head efivarfs_list; diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c index 8651ac28ec0d..dd029d13ea61 100644 --- a/fs/efivarfs/super.c +++ b/fs/efivarfs/super.c @@ -120,6 +120,7 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, char *name; int len; int err = -ENOMEM; + bool is_removable = false; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (!entry) @@ -137,13 +138,17 @@ static int efivarfs_callback(efi_char16_t *name16, efi_guid_t vendor, ucs2_as_utf8(name, entry->var.VariableName, len); + if (efivar_variable_is_removable(entry->var.VendorGuid, name, len)) + is_removable = true; + name[len] = '-'; efi_guid_to_str(&entry->var.VendorGuid, name + len + 1); name[len + EFI_VARIABLE_GUID_LEN+1] = '\0'; - inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0); + inode = efivarfs_get_inode(sb, d_inode(root), S_IFREG | 0644, 0, + is_removable); if (!inode) goto fail_name; @@ -199,7 +204,7 @@ static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_d_op = &efivarfs_d_ops; sb->s_time_gran = 1; - inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0, true); if (!inode) return -ENOMEM; inode->i_op = &efivarfs_dir_inode_operations; diff --git a/include/linux/efi.h b/include/linux/efi.h index 16ca611aabc8..47be3ad7d3e5 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1201,6 +1201,8 @@ struct efivar_entry *efivar_entry_find(efi_char16_t *name, efi_guid_t guid, bool efivar_validate(efi_guid_t vendor, efi_char16_t *var_name, u8 *data, unsigned long data_size); +bool efivar_variable_is_removable(efi_guid_t vendor, const char *name, + size_t len); extern struct work_struct efivar_work; void efivar_run_worker(void); diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index 77edcdcc016b..057278448515 100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh @@ -88,7 +88,11 @@ test_delete() exit 1 fi - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi if [ -e $file ]; then echo "$file couldn't be deleted" >&2 @@ -111,6 +115,7 @@ test_zero_size_delete() exit 1 fi + chattr -i $file printf "$attrs" > $file if [ -e $file ]; then @@ -141,7 +146,11 @@ test_valid_filenames() echo "$file could not be created" >&2 ret=1 else - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi fi done @@ -174,7 +183,11 @@ test_invalid_filenames() if [ -e $file ]; then echo "Creating $file should have failed" >&2 - rm $file + rm $file 2>/dev/null + if [ $? -ne 0 ]; then + chattr -i $file + rm $file + fi ret=1 fi done diff --git a/tools/testing/selftests/efivarfs/open-unlink.c b/tools/testing/selftests/efivarfs/open-unlink.c index 8c0764407b3c..4af74f733036 100644 --- a/tools/testing/selftests/efivarfs/open-unlink.c +++ b/tools/testing/selftests/efivarfs/open-unlink.c @@ -1,10 +1,68 @@ +#include #include #include #include #include +#include #include #include #include +#include + +static int set_immutable(const char *path, int immutable) +{ + unsigned int flags; + int fd; + int rc; + int error; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + rc = ioctl(fd, FS_IOC_GETFLAGS, &flags); + if (rc < 0) { + error = errno; + close(fd); + errno = error; + return rc; + } + + if (immutable) + flags |= FS_IMMUTABLE_FL; + else + flags &= ~FS_IMMUTABLE_FL; + + rc = ioctl(fd, FS_IOC_SETFLAGS, &flags); + error = errno; + close(fd); + errno = error; + return rc; +} + +static int get_immutable(const char *path) +{ + unsigned int flags; + int fd; + int rc; + int error; + + fd = open(path, O_RDONLY); + if (fd < 0) + return fd; + + rc = ioctl(fd, FS_IOC_GETFLAGS, &flags); + if (rc < 0) { + error = errno; + close(fd); + errno = error; + return rc; + } + close(fd); + if (flags & FS_IMMUTABLE_FL) + return 1; + return 0; +} int main(int argc, char **argv) { @@ -27,7 +85,7 @@ int main(int argc, char **argv) buf[4] = 0; /* create a test variable */ - fd = open(path, O_WRONLY | O_CREAT); + fd = open(path, O_WRONLY | O_CREAT, 0600); if (fd < 0) { perror("open(O_WRONLY)"); return EXIT_FAILURE; @@ -41,6 +99,18 @@ int main(int argc, char **argv) close(fd); + rc = get_immutable(path); + if (rc < 0) { + perror("ioctl(FS_IOC_GETFLAGS)"); + return EXIT_FAILURE; + } else if (rc) { + rc = set_immutable(path, 0); + if (rc < 0) { + perror("ioctl(FS_IOC_SETFLAGS)"); + return EXIT_FAILURE; + } + } + fd = open(path, O_RDONLY); if (fd < 0) { perror("open"); From df9cd56421635433ee42798fdf09138367039732 Mon Sep 17 00:00:00 2001 From: Linus Walleij Date: Wed, 3 Feb 2016 14:47:08 +0100 Subject: [PATCH 081/489] clk: versatile: mask VCO bits before writing The Versatile syscon ICST driver OR:s the bits into place but forgets to mask the previous value, making the code only work if the register is zero or giving haphazard results. Mask the 19 bits used by the Versatile syscon interface register. Regression caused and now fixed by yours truly. Cc: Michael Turquette Cc: Stephen Boyd Cc: linux-clk@vger.kernel.org Fixes: 179c8fb3c2a6 ("clk: versatile-icst: convert to use regmap") Signed-off-by: Linus Walleij Signed-off-by: Stephen Boyd --- drivers/clk/versatile/clk-icst.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/clk/versatile/clk-icst.c b/drivers/clk/versatile/clk-icst.c index e62f8cb2c9b5..3bca438ecd19 100644 --- a/drivers/clk/versatile/clk-icst.c +++ b/drivers/clk/versatile/clk-icst.c @@ -78,6 +78,9 @@ static int vco_set(struct clk_icst *icst, struct icst_vco vco) ret = regmap_read(icst->map, icst->vcoreg_off, &val); if (ret) return ret; + + /* Mask the 18 bits used by the VCO */ + val &= ~0x7ffff; val |= vco.v | (vco.r << 9) | (vco.s << 16); /* This magic unlocks the VCO so it can be controlled */ From 5f35dc47c1744110d4119c4aa2a00872e8a1217b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Wed, 10 Feb 2016 20:23:02 +0200 Subject: [PATCH 082/489] ARM: OMAP2+: Set system_rev from ATAGS for n900 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixed a regression with DT boot compared to legacy boot. Reviewed-by: Pali Rohár Tested-by: Pali Rohár Signed-off-by: Ivaylo Dimitrov [tony@atomide.com: edited patch subject to follow standard] Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/board-generic.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c index 809827265fb3..bab814d2f37d 100644 --- a/arch/arm/mach-omap2/board-generic.c +++ b/arch/arm/mach-omap2/board-generic.c @@ -18,6 +18,7 @@ #include #include +#include #include "common.h" @@ -77,12 +78,31 @@ static const char *const n900_boards_compat[] __initconst = { NULL, }; +/* Set system_rev from atags */ +static void __init rx51_set_system_rev(const struct tag *tags) +{ + const struct tag *tag; + + if (tags->hdr.tag != ATAG_CORE) + return; + + for_each_tag(tag, tags) { + if (tag->hdr.tag == ATAG_REVISION) { + system_rev = tag->u.revision.rev; + break; + } + } +} + /* Legacy userspace on Nokia N900 needs ATAGS exported in /proc/atags, * save them while the data is still not overwritten */ static void __init rx51_reserve(void) { - save_atags((const struct tag *)(PAGE_OFFSET + 0x100)); + const struct tag *tags = (const struct tag *)(PAGE_OFFSET + 0x100); + + save_atags(tags); + rx51_set_system_rev(tags); omap_reserve(); } From a5b87513119248c87b9df938025d066af8ec8856 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Mon, 8 Feb 2016 21:55:53 +0000 Subject: [PATCH 083/489] ARM: dts: am335x/am57xx: replace gpio-key,wakeup with wakeup-source property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 3efda00129bd ("ARM: dts: am335x: replace gpio-key,wakeup with wakeup-source property") replaces all the legacy "gpio-key,wakeup" with the unified "wakeup-source" property to prevent any further copy-paste duplication. However couple of use of these legacy property sneaked in during the merge window. This patch replaces them too. Cc: "Benoît Cousson" Cc: linux-omap@vger.kernel.org Signed-off-by: Sudeep Holla Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am335x-shc.dts | 4 ++-- arch/arm/boot/dts/am57xx-cl-som-am57x.dts | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/boot/dts/am335x-shc.dts b/arch/arm/boot/dts/am335x-shc.dts index 1b5b044fcd91..865de8500f1c 100644 --- a/arch/arm/boot/dts/am335x-shc.dts +++ b/arch/arm/boot/dts/am335x-shc.dts @@ -46,7 +46,7 @@ gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>; linux,code = ; debounce-interval = <1000>; - gpio-key,wakeup; + wakeup-source; }; front_button { @@ -54,7 +54,7 @@ gpios = <&gpio1 25 GPIO_ACTIVE_HIGH>; linux,code = ; debounce-interval = <1000>; - gpio-key,wakeup; + wakeup-source; }; }; diff --git a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts index 8d93882dc8d5..1c06cb76da07 100644 --- a/arch/arm/boot/dts/am57xx-cl-som-am57x.dts +++ b/arch/arm/boot/dts/am57xx-cl-som-am57x.dts @@ -545,7 +545,7 @@ ti,debounce-tol = /bits/ 16 <10>; ti,debounce-rep = /bits/ 16 <1>; - linux,wakeup; + wakeup-source; }; }; From bf26927b2c0780609e6e5361d177cf10107065f3 Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Tue, 9 Feb 2016 13:46:57 +0200 Subject: [PATCH 084/489] ARM: DTS: am57xx-beagle-x15: Select SYS_CLK2 for audio clocks The tlv320aic3104 codec's master clock is coming from the SoC's CLKOUT2. Select the SYS_CLK2 (via divider) as parent clock for CLKOUT2 and select the same clock (SYS_CLK2) for McASP3 AHCLKX clock as well. SYS_CLK2 is sourced from an external oscillator running 22.5792MHz and it is coming in to the SoC via the X1_OSC1. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- arch/arm/boot/dts/am57xx-beagle-x15.dts | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts index 36c0fa6c362a..a0986c65be0c 100644 --- a/arch/arm/boot/dts/am57xx-beagle-x15.dts +++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts @@ -173,6 +173,8 @@ sound0_master: simple-audio-card,codec { sound-dai = <&tlv320aic3104>; + assigned-clocks = <&clkoutmux2_clk_mux>; + assigned-clock-parents = <&sys_clk2_dclk_div>; clocks = <&clkout2_clk>; }; }; @@ -796,6 +798,8 @@ pinctrl-names = "default", "sleep"; pinctrl-0 = <&mcasp3_pins_default>; pinctrl-1 = <&mcasp3_pins_sleep>; + assigned-clocks = <&mcasp3_ahclkx_mux>; + assigned-clock-parents = <&sys_clkin2>; status = "okay"; op-mode = <0>; /* MCASP_IIS_MODE */ From 0986d97741150b307775d56f587a73ea873a4f4d Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 9 Feb 2016 16:23:39 +0100 Subject: [PATCH 085/489] s390: fix DAT off memory access, e.g. on kdump commit 204ee2c56431 ("s390/irqflags: optimize irq restore") optimized irqrestore to really only care about interrupts and adapted the remaining low level users. One spot (memcpy_real) was not touched, though - fix it. Otherwise a kdump kernel will fail while reading the old kernel. As we re-enable irqs with a non-standard function we have to tell lockdep about that. Fixes: 204ee2c56431 ("s390/irqflags: optimize irq restore") Signed-off-by: Christian Borntraeger Signed-off-by: Martin Schwidefsky --- arch/s390/mm/maccess.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index fec59c067d0d..350b0acd7f52 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -101,7 +101,9 @@ int memcpy_real(void *dest, void *src, size_t count) local_irq_save(flags); __arch_local_irq_stnsm(0xfbUL); rc = __memcpy_real(dest, src, count); - local_irq_restore(flags); + if (!arch_irqs_disabled_flags(flags)) + trace_hardirqs_on(); + __arch_local_irq_ssm(flags); return rc; } From 020bf042e5b397479c1174081b935d0ff15d1a64 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 15 Dec 2015 10:16:43 +0100 Subject: [PATCH 086/489] s390/dasd: prevent incorrect length error under z/VM after PAV changes The channel checks the specified length and the provided amount of data for CCWs and provides an incorrect length error if the size does not match. Under z/VM with simulation activated the length may get changed. Having the suppress length indication bit set is stated as good CCW coding practice and avoids errors under z/VM. Cc: stable@vger.kernel.org Signed-off-by: Stefan Haberland Signed-off-by: Martin Schwidefsky --- drivers/s390/block/dasd_alias.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 184b1dbeb554..4ff914c0f13c 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -723,7 +723,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu, ASCEBC((char *) &cqr->magic, 4); ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_RSCK; - ccw->flags = 0 ; + ccw->flags = CCW_FLAG_SLI; ccw->count = 16; ccw->cda = (__u32)(addr_t) cqr->data; ((char *)cqr->data)[0] = reason; From 9d862ababb609439c5d6987f6d3ddd09e703aa0b Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Tue, 15 Dec 2015 10:45:05 +0100 Subject: [PATCH 087/489] s390/dasd: fix refcount for PAV reassignment Add refcount to the DASD device when a summary unit check worker is scheduled. This prevents that the device is set offline with worker in place. Cc: stable@vger.kernel.org Signed-off-by: Stefan Haberland Signed-off-by: Martin Schwidefsky --- drivers/s390/block/dasd_alias.c | 21 ++++++++++++++++----- 1 file changed, 16 insertions(+), 5 deletions(-) diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c index 4ff914c0f13c..286782c60da4 100644 --- a/drivers/s390/block/dasd_alias.c +++ b/drivers/s390/block/dasd_alias.c @@ -264,8 +264,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) spin_unlock_irqrestore(&lcu->lock, flags); cancel_work_sync(&lcu->suc_data.worker); spin_lock_irqsave(&lcu->lock, flags); - if (device == lcu->suc_data.device) + if (device == lcu->suc_data.device) { + dasd_put_device(device); lcu->suc_data.device = NULL; + } } was_pending = 0; if (device == lcu->ruac_data.device) { @@ -273,8 +275,10 @@ void dasd_alias_disconnect_device_from_lcu(struct dasd_device *device) was_pending = 1; cancel_delayed_work_sync(&lcu->ruac_data.dwork); spin_lock_irqsave(&lcu->lock, flags); - if (device == lcu->ruac_data.device) + if (device == lcu->ruac_data.device) { + dasd_put_device(device); lcu->ruac_data.device = NULL; + } } private->lcu = NULL; spin_unlock_irqrestore(&lcu->lock, flags); @@ -549,8 +553,10 @@ static void lcu_update_work(struct work_struct *work) if ((rc && (rc != -EOPNOTSUPP)) || (lcu->flags & NEED_UAC_UPDATE)) { DBF_DEV_EVENT(DBF_WARNING, device, "could not update" " alias data in lcu (rc = %d), retry later", rc); - schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ); + if (!schedule_delayed_work(&lcu->ruac_data.dwork, 30*HZ)) + dasd_put_device(device); } else { + dasd_put_device(device); lcu->ruac_data.device = NULL; lcu->flags &= ~UPDATE_PENDING; } @@ -593,8 +599,10 @@ static int _schedule_lcu_update(struct alias_lcu *lcu, */ if (!usedev) return -EINVAL; + dasd_get_device(usedev); lcu->ruac_data.device = usedev; - schedule_delayed_work(&lcu->ruac_data.dwork, 0); + if (!schedule_delayed_work(&lcu->ruac_data.dwork, 0)) + dasd_put_device(usedev); return 0; } @@ -930,6 +938,7 @@ static void summary_unit_check_handling_work(struct work_struct *work) /* 3. read new alias configuration */ _schedule_lcu_update(lcu, device); lcu->suc_data.device = NULL; + dasd_put_device(device); spin_unlock_irqrestore(&lcu->lock, flags); } @@ -989,6 +998,8 @@ void dasd_alias_handle_summary_unit_check(struct dasd_device *device, } lcu->suc_data.reason = reason; lcu->suc_data.device = device; + dasd_get_device(device); spin_unlock(&lcu->lock); - schedule_work(&lcu->suc_data.worker); + if (!schedule_work(&lcu->suc_data.worker)) + dasd_put_device(device); }; From f6c9b160233f9b5afe926b91b55589b706076640 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Wed, 10 Feb 2016 14:13:24 +0100 Subject: [PATCH 088/489] s390/diag: avoid lockdep recursion The diagnose tracer will indirectly call back into the lockdep code when lockdep does not expect it (arch_spinlock). This causes lockdep to disable itself and therefore we don't have a working lock dependency validator anymore. This patch effectively disables tracing of diag 0x9c and 0x44 if lockdep is enabled. If however lockdep is enabled spinlocks are mainly implemented using a trylock variant, which will not issue any diag 0x9c or 0x44. So this change has hardly any effect on tracing except when arch_spinlock and friends are explicitly used. Reported-and-Tested-by: David Hildenbrand Signed-off-by: Heiko Carstens Reviewed-by: David Hildenbrand Acked-by: Martin Schwidefsky Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/trace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/s390/kernel/trace.c b/arch/s390/kernel/trace.c index 21a5df99552b..dde7654f5c68 100644 --- a/arch/s390/kernel/trace.c +++ b/arch/s390/kernel/trace.c @@ -18,6 +18,9 @@ void trace_s390_diagnose_norecursion(int diag_nr) unsigned long flags; unsigned int *depth; + /* Avoid lockdep recursion. */ + if (IS_ENABLED(CONFIG_LOCKDEP)) + return; local_irq_save(flags); depth = this_cpu_ptr(&diagnose_trace_depth); if (*depth == 0) { From 111f2b87326199a736c3469265763a6be6e5528f Mon Sep 17 00:00:00 2001 From: Krzysztof Adamski Date: Wed, 3 Feb 2016 08:57:14 +0100 Subject: [PATCH 089/489] pinctrl: sunxi: H3 requires irq_read_needs_mux It seems that on H3, just like on A10, when GPIOs are configured as external interrupt data registers does not contain their value. When value is read, GPIO function must be temporary switched to input for reads. Signed-off-by: Krzysztof Adamski Acked-by: Chen-Yu Tsai Acked-by: Maxime Ripard Signed-off-by: Linus Walleij --- drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c index 77d4cf047cee..11760bbe9d51 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-h3.c @@ -492,6 +492,7 @@ static const struct sunxi_pinctrl_desc sun8i_h3_pinctrl_data = { .pins = sun8i_h3_pins, .npins = ARRAY_SIZE(sun8i_h3_pins), .irq_banks = 2, + .irq_read_needs_mux = true }; static int sun8i_h3_pinctrl_probe(struct platform_device *pdev) From a514379b0c77085074abf01c525a850f6d99926e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Matias=20Bj=C3=B8rling?= Date: Thu, 11 Feb 2016 14:49:13 +0100 Subject: [PATCH 090/489] null_blk: oops when initializing without lightnvm MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If the LightNVM subsystem is not compiled into the kernel, and the null_blk device driver requests lightnvm to be initialized. The call to nvm_register fails and the null_add_dev function cleans up the initialization. However, at this point the null block device has already been added to the nullb_list and thus a second cleanup will occur when the function has returned, that leads to a double call to blk_cleanup_queue. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/block/null_blk.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index ae05d31c0559..64a7b5971b57 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -707,9 +707,7 @@ static int null_add_dev(void) queue_flag_set_unlocked(QUEUE_FLAG_NONROT, nullb->q); queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, nullb->q); - mutex_lock(&lock); - list_add_tail(&nullb->list, &nullb_list); nullb->index = nullb_indexes++; mutex_unlock(&lock); @@ -743,6 +741,10 @@ static int null_add_dev(void) strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN); add_disk(disk); + + mutex_lock(&lock); + list_add_tail(&nullb->list, &nullb_list); + mutex_unlock(&lock); done: return 0; From 004fa08d7aba2a13974446bf212a48c0b3b0d9fd Mon Sep 17 00:00:00 2001 From: Ashok Kumar Date: Thu, 11 Feb 2016 05:38:53 -0800 Subject: [PATCH 091/489] irqchip/gic-v3-its: Fix double ICC_EOIR write for LPI in EOImode==1 When the GIC is using EOImode==1, the EOI is done immediately, leaving the deactivation to be performed when the EOI was previously done. Unfortunately, the ITS is not aware of the EOImode at all, and blindly EOIs the interrupt again. On most systems, this is ignored (despite being a programming error), but some others do raise a SError exception as there is no priority drop to perform for this interrupt. The fix is to stop trying to be clever, and always call into the underlying GIC to perform the right access, irrespective of the more we're in. [Marc: Reworked commit message] Fixes: 0b996fd35957a ("irqchip/GICv3: Convert to EOImode == 1") Cc: stable@vger.kernel.org Acked-by: Marc Zyngier Signed-off-by: Ashok Kumar Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 0a73632b28d5..ff2be77a51f6 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -600,11 +600,6 @@ static void its_unmask_irq(struct irq_data *d) lpi_set_config(d, true); } -static void its_eoi_irq(struct irq_data *d) -{ - gic_write_eoir(d->hwirq); -} - static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -641,7 +636,7 @@ static struct irq_chip its_irq_chip = { .name = "ITS", .irq_mask = its_mask_irq, .irq_unmask = its_unmask_irq, - .irq_eoi = its_eoi_irq, + .irq_eoi = irq_chip_eoi_parent, .irq_set_affinity = its_set_affinity, .irq_compose_msi_msg = its_irq_compose_msi_msg, }; From 5f009d3f8e6685fe8c6215082c1696a08b411220 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 10 Feb 2016 16:52:47 -0700 Subject: [PATCH 092/489] block: Initialize max_dev_sectors to 0 The new queue limit is not used by the majority of block drivers, and should be initialized to 0 for the driver's requested settings to be used. Signed-off-by: Keith Busch Acked-by: Martin K. Petersen Reviewed-by: Sagi Grimberg Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-settings.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/blk-settings.c b/block/blk-settings.c index dd4973583978..c7bb666aafd1 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -91,8 +91,8 @@ void blk_set_default_limits(struct queue_limits *lim) lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK; lim->virt_boundary_mask = 0; lim->max_segment_size = BLK_MAX_SEGMENT_SIZE; - lim->max_sectors = lim->max_dev_sectors = lim->max_hw_sectors = - BLK_SAFE_MAX_SECTORS; + lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS; + lim->max_dev_sectors = 0; lim->chunk_sectors = 0; lim->max_write_same_sectors = 0; lim->max_discard_sectors = 0; From a59e0f5795fe52dad42a99c00287e3766153b312 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 11 Feb 2016 13:05:38 -0700 Subject: [PATCH 093/489] blk-mq: End unstarted requests on dying queue Go directly to ending a request if it wasn't started. Previously, completing a request may invoke a driver callback for a request it didn't initialize. Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 4c0622fae413..56c0a726b619 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -599,8 +599,10 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, * If a request wasn't started before the queue was * marked dying, kill it here or it'll go unnoticed. */ - if (unlikely(blk_queue_dying(rq->q))) - blk_mq_complete_request(rq, -EIO); + if (unlikely(blk_queue_dying(rq->q))) { + rq->errors = -EIO; + blk_mq_end_request(rq, rq->errors); + } return; } From 4f76d0e49835d3da33aa54811157421f7061805e Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 11 Feb 2016 13:05:39 -0700 Subject: [PATCH 094/489] NVMe: Fix io incapable return values The function returns true when the controller can't handle IO. Signed-off-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Johannes Thumshirn Acked-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/nvme/host/nvme.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 4fb5bb737868..9664d07d807d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -139,9 +139,9 @@ static inline bool nvme_io_incapable(struct nvme_ctrl *ctrl) u32 val = 0; if (ctrl->ops->io_incapable(ctrl)) - return false; + return true; if (ctrl->ops->reg_read32(ctrl, NVME_REG_CSTS, &val)) - return false; + return true; return val & NVME_CSTS_CFS; } From ef2d4615c59efb312e531a5e949970f37ca1c841 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 11 Feb 2016 13:05:40 -0700 Subject: [PATCH 095/489] NVMe: Allow request merges It is generally more efficient to submit larger IO. Signed-off-by: Keith Busch Reviewed-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/core.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index c5bf001af559..3cd921e6121e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1121,7 +1121,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) ns->queue = blk_mq_init_queue(ctrl->tagset); if (IS_ERR(ns->queue)) goto out_free_ns; - queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue); queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue); ns->queue->queuedata = ns; ns->ctrl = ctrl; From 5d589d81acf974d23af98044aac56c6339d659f8 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Tue, 9 Feb 2016 11:04:45 +0000 Subject: [PATCH 096/489] of/irq: Fix msi-map calculation for nonzero rid-base The existing msi-map code is fine for shifting the entire RID space upwards, but attempting finer-grained remapping reveals a bug. It turns out that we are mistakenly treating the msi-base part as an offset, not as a new base to remap onto, so things get squiffy when rid-base is nonzero. Fix this, and at the same time add a sanity check against having msi-map-mask clash with a nonzero rid-base, as that's another thing one can easily get wrong. CC: Signed-off-by: Robin Murphy Reviewed-by: Marc Zyngier Tested-by: Stuart Yoder Acked-by: Mark Rutland Acked-by: David Daney Signed-off-by: Rob Herring --- drivers/of/irq.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 7ee21ae305ae..e7bfc175b8e1 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -635,6 +635,13 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, msi_base = be32_to_cpup(msi_map + 2); rid_len = be32_to_cpup(msi_map + 3); + if (rid_base & ~map_mask) { + dev_err(parent_dev, + "Invalid msi-map translation - msi-map-mask (0x%x) ignores rid-base (0x%x)\n", + map_mask, rid_base); + return rid_out; + } + msi_controller_node = of_find_node_by_phandle(phandle); matched = (masked_rid >= rid_base && @@ -654,7 +661,7 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np, if (!matched) return rid_out; - rid_out = masked_rid + msi_base; + rid_out = masked_rid - rid_base + msi_base; dev_dbg(dev, "msi-map at: %s, using mask %08x, rid-base: %08x, msi-base: %08x, length: %08x, rid: %08x -> %08x\n", dev_name(parent_dev), map_mask, rid_base, msi_base, From 05145bd799e498ce4e3b5145894174ee881f02b0 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 11 Feb 2016 23:15:12 -0500 Subject: [PATCH 097/489] ext4: fix scheduling in atomic on group checksum failure When block group checksum is wrong, we call ext4_error() while holding group spinlock from ext4_init_block_bitmap() or ext4_init_inode_bitmap() which results in scheduling while in atomic. Fix the issue by calling ext4_error() later after dropping the spinlock. CC: stable@vger.kernel.org Reported-by: Dmitry Vyukov Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o Reviewed-by: Darrick J. Wong --- fs/ext4/balloc.c | 7 ++++--- fs/ext4/ialloc.c | 6 ++++-- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index ec0668a60678..fe1f50fe764f 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -191,7 +191,6 @@ static int ext4_init_block_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks used to prevent allocation * essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -442,14 +441,16 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group) } ext4_lock_group(sb, block_group); if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) { - err = ext4_init_block_bitmap(sb, bh, block_group, desc); set_bitmap_uptodate(bh); set_buffer_uptodate(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init block bitmap for group " + "%u: %d", block_group, err); goto out; + } goto verify; } ext4_unlock_group(sb, block_group); diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 3fcfd50a2e8a..acc0ad56bf2f 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -76,7 +76,6 @@ static int ext4_init_inode_bitmap(struct super_block *sb, /* If checksum is bad mark all blocks and inodes use to prevent * allocation, essentially implementing a per-group read-only flag. */ if (!ext4_group_desc_csum_verify(sb, block_group, gdp)) { - ext4_error(sb, "Checksum bad for group %u", block_group); grp = ext4_get_group_info(sb, block_group); if (!EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) percpu_counter_sub(&sbi->s_freeclusters_counter, @@ -191,8 +190,11 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group) set_buffer_verified(bh); ext4_unlock_group(sb, block_group); unlock_buffer(bh); - if (err) + if (err) { + ext4_error(sb, "Failed to init inode bitmap for group " + "%u: %d", block_group, err); goto out; + } return bh; } ext4_unlock_group(sb, block_group); From fdde368e7c2963e319f919fa57908537060847fc Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Thu, 11 Feb 2016 23:57:21 -0500 Subject: [PATCH 098/489] ext4: ioctl: fix erroneous return value The ext4_ioctl_setflags() function which is used in the ioctls EXT4_IOC_SETFLAGS and EXT4_IOC_FSSETXATTR may return the positive value EPERM instead of -EPERM in case of error. This bug was introduced by a recent commit 9b7365fc. The following program can be used to illustrate the wrong behavior: #include #include #include #include #include #define FS_IOC_GETFLAGS _IOR('f', 1, long) #define FS_IOC_SETFLAGS _IOW('f', 2, long) #define FS_IMMUTABLE_FL 0x00000010 int main(void) { int fd; long flags; fd = open("file", O_RDWR|O_CREAT, 0600); if (fd < 0) err(1, "open"); if (ioctl(fd, FS_IOC_GETFLAGS, &flags) < 0) err(1, "ioctl: FS_IOC_GETFLAGS"); flags |= FS_IMMUTABLE_FL; if (ioctl(fd, FS_IOC_SETFLAGS, &flags) < 0) err(1, "ioctl: FS_IOC_SETFLAGS"); warnx("ioctl returned no error"); return 0; } Running it gives the following result: $ strace -e ioctl ./test ioctl(3, FS_IOC_GETFLAGS, 0x7ffdbd8bfd38) = 0 ioctl(3, FS_IOC_SETFLAGS, 0x7ffdbd8bfd38) = 1 test: ioctl returned no error +++ exited with 0 +++ Running the program on a kernel with the bug fixed gives the proper result: $ strace -e ioctl ./test ioctl(3, FS_IOC_GETFLAGS, 0x7ffdd2768258) = 0 ioctl(3, FS_IOC_SETFLAGS, 0x7ffdd2768258) = -1 EPERM (Operation not permitted) test: ioctl: FS_IOC_SETFLAGS: Operation not permitted +++ exited with 1 +++ Signed-off-by: Anton Protopopov Signed-off-by: Theodore Ts'o --- fs/ext4/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 0f6c36922c24..a99b010e2194 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -208,7 +208,7 @@ static int ext4_ioctl_setflags(struct inode *inode, { struct ext4_inode_info *ei = EXT4_I(inode); handle_t *handle = NULL; - int err = EPERM, migrate = 0; + int err = -EPERM, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags, mask, i; unsigned int jflag; From 802cf1f9f504e09f7118c9acc69ab3e825449e52 Mon Sep 17 00:00:00 2001 From: Huaitong Han Date: Fri, 12 Feb 2016 00:17:16 -0500 Subject: [PATCH 099/489] ext4: add a line break for proc mb_groups display This patch adds a line break for proc mb_groups display. Signed-off-by: Huaitong Han Signed-off-by: Theodore Ts'o Reviewed-by: Andreas Dilger --- fs/ext4/mballoc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 61eaf74dca37..4424b7bf8ac6 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -2285,7 +2285,7 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v) if (group == 0) seq_puts(seq, "#group: free frags first [" " 2^0 2^1 2^2 2^3 2^4 2^5 2^6 " - " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]"); + " 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n"); i = (sb->s_blocksize_bits + 2) * sizeof(sg.info.bb_counters[0]) + sizeof(struct ext4_group_info); From 90a88d6ef88edcfc4f644dddc7eef4ea41bccf8b Mon Sep 17 00:00:00 2001 From: James Bottomley Date: Wed, 10 Feb 2016 08:03:26 -0800 Subject: [PATCH 100/489] scsi: fix soft lockup in scsi_remove_target() on module removal This softlockup is currently happening: [ 444.088002] NMI watchdog: BUG: soft lockup - CPU#1 stuck for 22s! [kworker/1:1:29] [ 444.088002] Modules linked in: lpfc(-) qla2x00tgt(O) qla2xxx_scst(O) scst_vdisk(O) scsi_transport_fc libcrc32c scst(O) dlm configfs nfsd lockd grace nfs_acl auth_rpcgss sunrpc ed d snd_pcm_oss snd_mixer_oss snd_seq snd_seq_device dm_mod iTCO_wdt snd_hda_codec_realtek snd_hda_codec_generic gpio_ich iTCO_vendor_support ppdev snd_hda_intel snd_hda_codec snd_hda _core snd_hwdep tg3 snd_pcm snd_timer libphy lpc_ich parport_pc ptp acpi_cpufreq snd pps_core fjes parport i2c_i801 ehci_pci tpm_tis tpm sr_mod cdrom soundcore floppy hwmon sg 8250_ fintek pcspkr i915 drm_kms_helper uhci_hcd ehci_hcd drm fb_sys_fops sysimgblt sysfillrect syscopyarea i2c_algo_bit usbcore button video usb_common fan ata_generic ata_piix libata th ermal [ 444.088002] CPU: 1 PID: 29 Comm: kworker/1:1 Tainted: G O 4.4.0-rc5-2.g1e923a3-default #1 [ 444.088002] Hardware name: FUJITSU SIEMENS ESPRIMO E /D2164-A1, BIOS 5.00 R1.10.2164.A1 05/08/2006 [ 444.088002] Workqueue: fc_wq_4 fc_rport_final_delete [scsi_transport_fc] [ 444.088002] task: f6266ec0 ti: f6268000 task.ti: f6268000 [ 444.088002] EIP: 0060:[] EFLAGS: 00000286 CPU: 1 [ 444.088002] EIP is at _raw_spin_unlock_irqrestore+0x14/0x20 [ 444.088002] EAX: 00000286 EBX: f20d3800 ECX: 00000002 EDX: 00000286 [ 444.088002] ESI: f50ba800 EDI: f2146848 EBP: f6269ec8 ESP: f6269ec8 [ 444.088002] DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 [ 444.088002] CR0: 8005003b CR2: 08f96600 CR3: 363ae000 CR4: 000006d0 [ 444.088002] Stack: [ 444.088002] f6269eec c066b0f7 00000286 f2146848 f50ba808 f50ba800 f50ba800 f2146a90 [ 444.088002] f2146848 f6269f08 f8f0a4ed f3141000 f2146800 f2146a90 f619fa00 00000040 [ 444.088002] f6269f40 c026cb25 00000001 166c6392 00000061 f6757140 f6136340 00000004 [ 444.088002] Call Trace: [ 444.088002] [] scsi_remove_target+0x167/0x1c0 [ 444.088002] [] fc_rport_final_delete+0x9d/0x1e0 [scsi_transport_fc] [ 444.088002] [] process_one_work+0x155/0x3e0 [ 444.088002] [] worker_thread+0x37/0x490 [ 444.088002] [] kthread+0x9b/0xb0 [ 444.088002] [] ret_from_kernel_thread+0x21/0x40 What appears to be happening is that something has pinned the target so it can't go into STARGET_DEL via final release and the loop in scsi_remove_target spins endlessly until that happens. The fix for this soft lockup is to not keep looping over a device that we've called remove on but which hasn't gone into DEL state. This patch will retain a simplistic memory of the last target and not keep looping over it. Reported-by: Sebastian Herbszt Tested-by: Sebastian Herbszt Fixes: 40998193560dab6c3ce8d25f4fa58a23e252ef38 Cc: stable@vger.kernel.org Signed-off-by: James Bottomley --- drivers/scsi/scsi_sysfs.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 4f18a851e2c7..00bc7218a7f8 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1272,16 +1272,18 @@ static void __scsi_remove_target(struct scsi_target *starget) void scsi_remove_target(struct device *dev) { struct Scsi_Host *shost = dev_to_shost(dev->parent); - struct scsi_target *starget; + struct scsi_target *starget, *last_target = NULL; unsigned long flags; restart: spin_lock_irqsave(shost->host_lock, flags); list_for_each_entry(starget, &shost->__targets, siblings) { - if (starget->state == STARGET_DEL) + if (starget->state == STARGET_DEL || + starget == last_target) continue; if (starget->dev.parent == dev || &starget->dev == dev) { kref_get(&starget->reap_ref); + last_target = starget; spin_unlock_irqrestore(shost->host_lock, flags); __scsi_remove_target(starget); scsi_target_reap(starget); From 46901760b46064964b41015d00c140c83aa05bcf Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Fri, 12 Feb 2016 01:15:59 -0500 Subject: [PATCH 101/489] ext4: fix potential integer overflow Since sizeof(ext_new_group_data) > sizeof(ext_new_flex_group_data), integer overflow could be happened. Therefore, need to fix integer overflow sanitization. Cc: stable@vger.kernel.org Signed-off-by: Insu Yun Signed-off-by: Theodore Ts'o --- fs/ext4/resize.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c index ad62d7acc315..34038e3598d5 100644 --- a/fs/ext4/resize.c +++ b/fs/ext4/resize.c @@ -198,7 +198,7 @@ static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size) if (flex_gd == NULL) goto out3; - if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_flex_group_data)) + if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data)) goto out2; flex_gd->count = flexbg_size; From bcff24887d00bce102e0857d7b0a8c44a40f53d1 Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Fri, 12 Feb 2016 01:20:43 -0500 Subject: [PATCH 102/489] ext4: don't read blocks from disk after extents being swapped I notice ext4/307 fails occasionally on ppc64 host, reporting md5 checksum mismatch after moving data from original file to donor file. The reason is that move_extent_per_page() calls __block_write_begin() and block_commit_write() to write saved data from original inode blocks to donor inode blocks, but __block_write_begin() not only maps buffer heads but also reads block content from disk if the size is not block size aligned. At this time the physical block number in mapped buffer head is pointing to the donor file not the original file, and that results in reading wrong data to page, which get written to disk in following block_commit_write call. This also can be reproduced by the following script on 1k block size ext4 on x86_64 host: mnt=/mnt/ext4 donorfile=$mnt/donor testfile=$mnt/testfile e4compact=~/xfstests/src/e4compact rm -f $donorfile $testfile # reserve space for donor file, written by 0xaa and sync to disk to # avoid EBUSY on EXT4_IOC_MOVE_EXT xfs_io -fc "pwrite -S 0xaa 0 1m" -c "fsync" $donorfile # create test file written by 0xbb xfs_io -fc "pwrite -S 0xbb 0 1023" -c "fsync" $testfile # compute initial md5sum md5sum $testfile | tee md5sum.txt # drop cache, force e4compact to read data from disk echo 3 > /proc/sys/vm/drop_caches # test defrag echo "$testfile" | $e4compact -i -v -f $donorfile # check md5sum md5sum -c md5sum.txt Fix it by creating & mapping buffer heads only but not reading blocks from disk, because all the data in page is guaranteed to be up-to-date in mext_page_mkuptodate(). Cc: stable@vger.kernel.org Signed-off-by: Eryu Guan Signed-off-by: Theodore Ts'o --- fs/ext4/move_extent.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index fb6f11709ae6..e032a0423e35 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -265,11 +265,12 @@ move_extent_per_page(struct file *o_filp, struct inode *donor_inode, ext4_lblk_t orig_blk_offset, donor_blk_offset; unsigned long blocksize = orig_inode->i_sb->s_blocksize; unsigned int tmp_data_size, data_size, replaced_size; - int err2, jblocks, retries = 0; + int i, err2, jblocks, retries = 0; int replaced_count = 0; int from = data_offset_in_page << orig_inode->i_blkbits; int blocks_per_page = PAGE_CACHE_SIZE >> orig_inode->i_blkbits; struct super_block *sb = orig_inode->i_sb; + struct buffer_head *bh = NULL; /* * It needs twice the amount of ordinary journal buffers because @@ -380,8 +381,16 @@ data_copy: } /* Perform all necessary steps similar write_begin()/write_end() * but keeping in mind that i_size will not change */ - *err = __block_write_begin(pagep[0], from, replaced_size, - ext4_get_block); + if (!page_has_buffers(pagep[0])) + create_empty_buffers(pagep[0], 1 << orig_inode->i_blkbits, 0); + bh = page_buffers(pagep[0]); + for (i = 0; i < data_offset_in_page; i++) + bh = bh->b_this_page; + for (i = 0; i < block_len_in_page; i++) { + *err = ext4_get_block(orig_inode, orig_blk_offset + i, bh, 0); + if (*err < 0) + break; + } if (!*err) *err = block_commit_write(pagep[0], from, from + replaced_size); From 56263b4ceba90b1db77a6b31e22726f101bca807 Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Fri, 12 Feb 2016 01:23:00 -0500 Subject: [PATCH 103/489] ext4: remove unused parameter "newblock" in convert_initialized_extent() The "newblock" parameter is not used in convert_initialized_extent(), remove it. Signed-off-by: Eryu Guan Signed-off-by: Theodore Ts'o --- fs/ext4/extents.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0ffabaf90aa5..3753ceb0b0dd 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -3928,7 +3928,7 @@ static int convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path **ppath, int flags, - unsigned int allocated, ext4_fsblk_t newblock) + unsigned int allocated) { struct ext4_ext_path *path = *ppath; struct ext4_extent *ex; @@ -4347,7 +4347,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { allocated = convert_initialized_extent( handle, inode, map, &path, - flags, allocated, newblock); + flags, allocated); goto out2; } else if (!ext4_ext_is_unwritten(ex)) goto out; From fb724ed5c6175a2407b256d506c9e703c6bb62d4 Mon Sep 17 00:00:00 2001 From: Emil Goode Date: Wed, 10 Feb 2016 02:22:16 +0100 Subject: [PATCH 104/489] wlcore: Fix regression in wlcore_set_partition() The commit 3719c17e1816 ("wlcore/wl18xx: fw logger over sdio") introduced a regression causing the wlcore to time out and go into recovery. Reverting the changes regarding write of the last partition size brings the module back to it's functional state. Fixes: 3719c17e1816 ("wlcore/wl18xx: fw logger over sdio") Reported-by: Ross Green Signed-off-by: Emil Goode [kvalo@codeaurora.org: improved commit log] Signed-off-by: Kalle Valo --- drivers/net/wireless/ti/wlcore/io.c | 8 ++++---- drivers/net/wireless/ti/wlcore/io.h | 4 ++-- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/wireless/ti/wlcore/io.c b/drivers/net/wireless/ti/wlcore/io.c index 9ac118e727e9..564ca750c5ee 100644 --- a/drivers/net/wireless/ti/wlcore/io.c +++ b/drivers/net/wireless/ti/wlcore/io.c @@ -175,14 +175,14 @@ int wlcore_set_partition(struct wl1271 *wl, if (ret < 0) goto out; + /* We don't need the size of the last partition, as it is + * automatically calculated based on the total memory size and + * the sizes of the previous partitions. + */ ret = wlcore_raw_write32(wl, HW_PART3_START_ADDR, p->mem3.start); if (ret < 0) goto out; - ret = wlcore_raw_write32(wl, HW_PART3_SIZE_ADDR, p->mem3.size); - if (ret < 0) - goto out; - out: return ret; } diff --git a/drivers/net/wireless/ti/wlcore/io.h b/drivers/net/wireless/ti/wlcore/io.h index 6c257b54f415..10cf3747694d 100644 --- a/drivers/net/wireless/ti/wlcore/io.h +++ b/drivers/net/wireless/ti/wlcore/io.h @@ -36,8 +36,8 @@ #define HW_PART1_START_ADDR (HW_PARTITION_REGISTERS_ADDR + 12) #define HW_PART2_SIZE_ADDR (HW_PARTITION_REGISTERS_ADDR + 16) #define HW_PART2_START_ADDR (HW_PARTITION_REGISTERS_ADDR + 20) -#define HW_PART3_SIZE_ADDR (HW_PARTITION_REGISTERS_ADDR + 24) -#define HW_PART3_START_ADDR (HW_PARTITION_REGISTERS_ADDR + 28) +#define HW_PART3_START_ADDR (HW_PARTITION_REGISTERS_ADDR + 24) + #define HW_ACCESS_REGISTER_SIZE 4 #define HW_ACCESS_PRAM_MAX_RANGE 0x3c000 From ae1fba20015bca7401db2422fe18c9c049184163 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 11 Feb 2016 13:05:42 -0700 Subject: [PATCH 105/489] NVMe: Requeue requests on suspended queues It's possible a request may get to the driver after the nvme queue was disabled. This has the request requeue if that happens. Note the request is still "started" by the driver, but requeuing will clear the start state for timeout handling. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 72ef8322d32a..e5c2bea01dbf 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -678,6 +678,11 @@ static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(req); spin_lock_irq(&nvmeq->q_lock); + if (unlikely(nvmeq->cq_vector < 0)) { + ret = BLK_MQ_RQ_QUEUE_BUSY; + spin_unlock_irq(&nvmeq->q_lock); + goto out; + } __nvme_submit_cmd(nvmeq, &cmnd); nvme_process_cq(nvmeq); spin_unlock_irq(&nvmeq->q_lock); From ff23a2a15a2117245b4599c1352343c8b8fb4c43 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 11 Feb 2016 13:05:43 -0700 Subject: [PATCH 106/489] NVMe: Poll device while still active during remove A device failure or link down wouldn't have been detected during namespace removal. This patch keeps the device in the list for polling so that the thread may see such failure and initiate a reset. The device is removed from the list after disable, so we can safely flush the reset work as it can't be requeued when disable completes. Signed-off-by: Keith Busch Reviewed-by: Christoph Hellwig Reviewed-by: Johannes Thumshirn Reviewed-by: Sagi Grimberg Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index e5c2bea01dbf..09cc4dafa32a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -2116,16 +2116,12 @@ static void nvme_remove(struct pci_dev *pdev) { struct nvme_dev *dev = pci_get_drvdata(pdev); - spin_lock(&dev_list_lock); - list_del_init(&dev->node); - spin_unlock(&dev_list_lock); - pci_set_drvdata(pdev, NULL); - flush_work(&dev->reset_work); flush_work(&dev->scan_work); nvme_remove_namespaces(&dev->ctrl); nvme_uninit_ctrl(&dev->ctrl); nvme_dev_disable(dev, true); + flush_work(&dev->reset_work); nvme_dev_remove_admin(dev); nvme_free_queues(dev, 0); nvme_release_cmb(dev); From f8e68a7c9af5f8047f7f8295874bedf306063709 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Thu, 11 Feb 2016 13:05:47 -0700 Subject: [PATCH 107/489] NVMe: Rate limit nvme IO warnings We don't need to spam the kernel logs with thousands of IO cancelling messages. We can infer all IO's are being cancelled with fewer, or even none at all. This patch rate limits the message and uses the debug log level as it is mainly used for testing purposes. Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/nvme/host/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 09cc4dafa32a..a128672472ec 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1004,7 +1004,7 @@ static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved if (!blk_mq_request_started(req)) return; - dev_warn(nvmeq->q_dmadev, + dev_dbg_ratelimited(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n", req->tag, nvmeq->qid); status = NVME_SC_ABORT_REQ; From 2d99b55d378c996b9692a0c93dd25f4ed5d58934 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Fri, 12 Feb 2016 09:39:15 +0100 Subject: [PATCH 108/489] bio: return EINTR if copying to user space got interrupted Commit 35dc248383bbab0a7203fca4d722875bc81ef091 introduced a check for current->mm to see if we have a user space context and only copies data if we do. Now if an IO gets interrupted by a signal data isn't copied into user space any more (as we don't have a user space context) but user space isn't notified about it. This patch modifies the behaviour to return -EINTR from bio_uncopy_user() to notify userland that a signal has interrupted the syscall, otherwise it could lead to a situation where the caller may get a buffer with no data returned. This can be reproduced by issuing SG_IO ioctl()s in one thread while constantly sending signals to it. Fixes: 35dc248 [SCSI] sg: Fix user memory corruption when SG_IO is interrupted by a signal Signed-off-by: Johannes Thumshirn Signed-off-by: Hannes Reinecke Cc: stable@vger.kernel.org # v.3.11+ Signed-off-by: Jens Axboe --- block/bio.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/block/bio.c b/block/bio.c index f53a691b6533..cf7591551b17 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1090,9 +1090,12 @@ int bio_uncopy_user(struct bio *bio) if (!bio_flagged(bio, BIO_NULL_MAPPED)) { /* * if we're in a workqueue, the request is orphaned, so - * don't copy into a random user address space, just free. + * don't copy into a random user address space, just free + * and return -EINTR so user space doesn't expect any data. */ - if (current->mm && bio_data_dir(bio) == READ) + if (!current->mm) + ret = -EINTR; + else if (bio_data_dir(bio) == READ) ret = bio_copy_to_iter(bio, bmd->iter); if (bmd->is_our_pages) bio_free_pages(bio); From a80a0eb70c358f8c7dda4bb62b2278dc6285217b Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Thu, 11 Feb 2016 13:53:10 -0800 Subject: [PATCH 109/489] arm64: make irq_stack_ptr more robust Switching between stacks is only valid if we are tracing ourselves while on the irq_stack, so it is only valid when in current and non-preemptible context, otherwise is is just zeroed off. Fixes: 132cd887b5c5 ("arm64: Modify stack trace and dump for use with irq_stack") Acked-by: James Morse Tested-by: James Morse Signed-off-by: Yang Shi Signed-off-by: Will Deacon --- arch/arm64/kernel/stacktrace.c | 13 ++++++------- arch/arm64/kernel/traps.c | 11 ++++++++++- 2 files changed, 16 insertions(+), 8 deletions(-) diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 12a18cbc4295..d9751a4769e7 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -44,14 +44,13 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long irq_stack_ptr; /* - * Use raw_smp_processor_id() to avoid false-positives from - * CONFIG_DEBUG_PREEMPT. get_wchan() calls unwind_frame() on sleeping - * task stacks, we can be pre-empted in this case, so - * {raw_,}smp_processor_id() may give us the wrong value. Sleeping - * tasks can't ever be on an interrupt stack, so regardless of cpu, - * the checks will always fail. + * Switching between stacks is valid when tracing current and in + * non-preemptible context. */ - irq_stack_ptr = IRQ_STACK_PTR(raw_smp_processor_id()); + if (tsk == current && !preemptible()) + irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + else + irq_stack_ptr = 0; low = frame->sp; /* irq stacks are not THREAD_SIZE aligned */ diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index cbedd724f48e..c5392081b49b 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -146,9 +146,18 @@ static void dump_instr(const char *lvl, struct pt_regs *regs) static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) { struct stackframe frame; - unsigned long irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + unsigned long irq_stack_ptr; int skip; + /* + * Switching between stacks is valid when tracing current and in + * non-preemptible context. + */ + if (tsk == current && !preemptible()) + irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id()); + else + irq_stack_ptr = 0; + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); if (!tsk) From 08c78e9d61a857c9077240e7ddb67550c6f96d06 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 12 Feb 2016 08:56:52 -0800 Subject: [PATCH 110/489] ARM: OMAP2+: Improve omap_device error for driver writers Drivers using pm_runtime_use_autosuspend() may not get disabled after -EPROBE_DEFER. On the following device driver probe, hardware state is different from the PM runtime state causing omap_device to produce the following error: omap_device_enable() called from invalid state 1 And with omap_device and omap hardware being picky for PM, this will block any deeper idle states in hardware. Let's add a proper error message so driver writers can easily fix their drivers for PM. In general, the solution is to fix the drivers to follow the PM runtime documentation: 1. For sections of code that needs the device disabled, use pm_runtime_put_sync_suspend() if pm_runtime_set_autosuspend() has been set. 2. For driver exit code, use pm_runtime_dont_use_autosuspend() before pm_runtime_put_sync() if pm_runtime_use_autosuspend() has been set. Let's not return with 0 from _od_runtime_resume() as that will eventually lead into new drivers with broken PM runtime that will block deeper idle states on omaps. Cc: Alan Stern Cc: Nishanth Menon Cc: Rafael J. Wysocki Cc: Tero Kristo Acked-by: Kevin Hilman Acked-by: Ulf Hansson Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_device.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index 0437537751bc..ebd83690ba48 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -602,8 +602,10 @@ static int _od_runtime_resume(struct device *dev) int ret; ret = omap_device_enable(pdev); - if (ret) + if (ret) { + dev_err(dev, "use pm_runtime_put_sync_suspend() in driver?\n"); return ret; + } return pm_generic_runtime_resume(dev); } From cf26f1137333251f3515dea31f95775b99df0fd5 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Fri, 12 Feb 2016 08:56:52 -0800 Subject: [PATCH 111/489] ARM: OMAP2+: Fix omap_device for module reload on PM runtime forbid If a driver PM runtime is disabled via sysfs, and the module is unloaded, PM runtime can't do anything to disable the device. Let's let the interconnect disable the device on BUS_NOTIFY_UNBOUND_DRIVER. Otherwise omap_device will produce and error on the following module reload. This can be easily tested with something like: # modprobe omap_hsmmc # echo on > /sys/devices/platform/68000000.ocp/4809c000.mmc/power/control # rmmod omap_hsmmc # modprobe omap_hsmmc Cc: Alan Stern Cc: Nishanth Menon Cc: Rafael J. Wysocki Cc: Tero Kristo Reported-by: Ulf Hansson Acked-by: Kevin Hilman Acked-by: Ulf Hansson Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/omap_device.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c index ebd83690ba48..f7ff3b9dad87 100644 --- a/arch/arm/mach-omap2/omap_device.c +++ b/arch/arm/mach-omap2/omap_device.c @@ -191,12 +191,22 @@ static int _omap_device_notifier_call(struct notifier_block *nb, { struct platform_device *pdev = to_platform_device(dev); struct omap_device *od; + int err; switch (event) { case BUS_NOTIFY_DEL_DEVICE: if (pdev->archdata.od) omap_device_delete(pdev->archdata.od); break; + case BUS_NOTIFY_UNBOUND_DRIVER: + od = to_omap_device(pdev); + if (od && (od->_state == OMAP_DEVICE_STATE_ENABLED)) { + dev_info(dev, "enabled after unload, idling\n"); + err = omap_device_idle(pdev); + if (err) + dev_err(dev, "failed to idle\n"); + } + break; case BUS_NOTIFY_ADD_DEVICE: if (pdev->dev.of_node) omap_device_build_from_dt(pdev); From e6244deed843bc001697f37e5beb1c0daf4f46a4 Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 10 Feb 2016 15:02:45 -0800 Subject: [PATCH 112/489] i2c: omap: Fix PM regression with deferred probe for pm_runtime_reinit Commit 5de85b9d57ab ("PM / runtime: Re-init runtime PM states at probe error and driver unbind") introduced pm_runtime_reinit() that is used to reinitialize PM runtime after -EPROBE_DEFER. This allows shutting down the device after a failed probe. However, for drivers using pm_runtime_use_autosuspend() this can cause a state where suspend callback is never called after -EPROBE_DEFER. On the following device driver probe, hardware state is different from the PM runtime state causing omap_device to produce the following error: omap_device_enable() called from invalid state 1 And with omap_device and omap hardware being picky for PM, this will block any deeper idle states in hardware. The solution is to fix the drivers to follow the PM runtime documentation: 1. For sections of code that needs the device disabled, use pm_runtime_put_sync_suspend() if pm_runtime_set_autosuspend() has been set. 2. For driver exit code, use pm_runtime_dont_use_autosuspend() before pm_runtime_put_sync() if pm_runtime_use_autosuspend() has been set. Fixes: 5de85b9d57ab ("PM / runtime: Re-init runtime PM states at probe error and driver unbind") Signed-off-by: Tony Lindgren Acked-by: Ulf Hansson Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-omap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 08d26ba61ed3..13c45296ce5b 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1450,7 +1450,8 @@ omap_i2c_probe(struct platform_device *pdev) err_unuse_clocks: omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0); - pm_runtime_put(omap->dev); + pm_runtime_dont_use_autosuspend(omap->dev); + pm_runtime_put_sync(omap->dev); pm_runtime_disable(&pdev->dev); err_free_mem: @@ -1468,6 +1469,7 @@ static int omap_i2c_remove(struct platform_device *pdev) return ret; omap_i2c_write_reg(omap, OMAP_I2C_CON_REG, 0); + pm_runtime_dont_use_autosuspend(&pdev->dev); pm_runtime_put_sync(&pdev->dev); pm_runtime_disable(&pdev->dev); return 0; From bca71ba0343d28d953d74149d9161ab65a520dd6 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Tue, 26 Jan 2016 18:09:21 +0900 Subject: [PATCH 113/489] i2c: uniphier: fix typos in error messages Signed-off-by: Masahiro Yamada Signed-off-by: Wolfram Sang --- drivers/i2c/busses/i2c-uniphier-f.c | 2 +- drivers/i2c/busses/i2c-uniphier.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-uniphier-f.c b/drivers/i2c/busses/i2c-uniphier-f.c index f3e5ff8522f0..213ba55e17c3 100644 --- a/drivers/i2c/busses/i2c-uniphier-f.c +++ b/drivers/i2c/busses/i2c-uniphier-f.c @@ -467,7 +467,7 @@ static int uniphier_fi2c_clk_init(struct device *dev, bus_speed = UNIPHIER_FI2C_DEFAULT_SPEED; if (!bus_speed) { - dev_err(dev, "clock-freqyency should not be zero\n"); + dev_err(dev, "clock-frequency should not be zero\n"); return -EINVAL; } diff --git a/drivers/i2c/busses/i2c-uniphier.c b/drivers/i2c/busses/i2c-uniphier.c index 1f4f3f53819c..89eaa8a7e1e0 100644 --- a/drivers/i2c/busses/i2c-uniphier.c +++ b/drivers/i2c/busses/i2c-uniphier.c @@ -328,7 +328,7 @@ static int uniphier_i2c_clk_init(struct device *dev, bus_speed = UNIPHIER_I2C_DEFAULT_SPEED; if (!bus_speed) { - dev_err(dev, "clock-freqyency should not be zero\n"); + dev_err(dev, "clock-frequency should not be zero\n"); return -EINVAL; } From 4aff7b854611d91c5fefb1553eb4c328123095ae Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Wed, 3 Feb 2016 18:00:58 +0000 Subject: [PATCH 114/489] dt-bindings: arm, gic-v3: require that reserved cells are always 0 The arm,gic-v3 binding was written with good intentions and doesn't enforce interrupt-cells to be 3, therefore making it easy to extend the irq description in future if necessary: > Cells 4 and beyond are reserved for future use. Unfortunately, this sentence is immediately followed up with: > When the 1st cell has a value of 0 or 1, cells 4 and beyond act as > padding, and may be ignored. It is recommended that padding cells > have a value of 0. Consequently, any extensions to the PPI or SPI interrupt specifiers must be able to work with random crap from legacy DTs, effectively necessitating a new interrupt type in the first cell. Sigh. This patch fixes the text so that additional, reserved cells are required to be zero. This looks like a reasonable thing to require and is already satisifed by the .dts files in-tree. Cc: Mark Rutland Cc: Marc Zyngier Signed-off-by: Will Deacon Acked-by: Marc Zyngier Acked-by: Mark Rutland Signed-off-by: Rob Herring --- .../devicetree/bindings/interrupt-controller/arm,gic-v3.txt | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt index 7803e77d85cb..007a5b46256a 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt +++ b/Documentation/devicetree/bindings/interrupt-controller/arm,gic-v3.txt @@ -24,9 +24,8 @@ Main node required properties: 1 = edge triggered 4 = level triggered - Cells 4 and beyond are reserved for future use. When the 1st cell - has a value of 0 or 1, cells 4 and beyond act as padding, and may be - ignored. It is recommended that padding cells have a value of 0. + Cells 4 and beyond are reserved for future use and must have a value + of 0 if present. - reg : Specifies base physical address(s) and size of the GIC registers, in the following order: From 32e593b9c7be1a14d42ed288ab68a8e7b41ad873 Mon Sep 17 00:00:00 2001 From: Fabio Estevam Date: Fri, 5 Feb 2016 17:44:22 -0200 Subject: [PATCH 115/489] serial: fsl-imx-uart: Fix typo in fsl,dte-mode description We should say "The uart works in DCE mode". Signed-off-by: Fabio Estevam Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/serial/fsl-imx-uart.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt index 35ae1fb3537f..ed94c217c98d 100644 --- a/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt +++ b/Documentation/devicetree/bindings/serial/fsl-imx-uart.txt @@ -9,7 +9,7 @@ Optional properties: - fsl,uart-has-rtscts : Indicate the uart has rts and cts - fsl,irda-mode : Indicate the uart supports irda mode - fsl,dte-mode : Indicate the uart works in DTE mode. The uart works - is DCE mode by default. + in DCE mode by default. Note: Each uart controller should have an alias correctly numbered in "aliases" node. From 43f3408261a2fd5054ada359efa15f0b78faf0a7 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Tue, 9 Feb 2016 14:23:52 -0300 Subject: [PATCH 116/489] rtc: s3c: Document required clocks in the DT binding The S3C Real Time Clock driver requires the clock and source clock to be defined in the device node but that requirement is not documented. Signed-off-by: Javier Martinez Canillas Signed-off-by: Rob Herring --- Documentation/devicetree/bindings/rtc/s3c-rtc.txt | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt index ac2fcd6ff4b8..1068ffce9f91 100644 --- a/Documentation/devicetree/bindings/rtc/s3c-rtc.txt +++ b/Documentation/devicetree/bindings/rtc/s3c-rtc.txt @@ -14,6 +14,10 @@ Required properties: interrupt number is the rtc alarm interrupt and second interrupt number is the rtc tick interrupt. The number of cells representing a interrupt depends on the parent interrupt controller. +- clocks: Must contain a list of phandle and clock specifier for the rtc + and source clocks. +- clock-names: Must contain "rtc" and "rtc_src" entries sorted in the + same order as the clocks property. Example: @@ -21,4 +25,6 @@ Example: compatible = "samsung,s3c6410-rtc"; reg = <0x10070000 0x100>; interrupts = <44 0 45 0>; + clocks = <&clock CLK_RTC>, <&s2mps11_osc S2MPS11_CLK_AP>; + clock-names = "rtc", "rtc_src"; }; From c430daf951c56e1eaf47c1825dcd5574f95ed29a Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Fri, 12 Feb 2016 09:21:13 -0800 Subject: [PATCH 117/489] Revert "clk: qcom: Specify LE device endianness" This reverts commit 329cabcecf94d8d7821e729dda284ba9dec44c87. The commit that caused us to specify LE device endianness here, 29bb45f25ff3 (regmap-mmio: Use native endianness for read/write, 2015-10-29), has been reverted in mainline so now when we specify LE it actively breaks big endian kernels because the byte swapping in regmap-mmio is incorrect. Let's revert this change because it will 1) fix the big endian kernels and 2) be redundant to specify LE because that will become the default soon. Cc: Kevin Hilman Tested-by: Kevin Hilman Cc: Mark Brown Signed-off-by: Stephen Boyd --- drivers/clk/qcom/gcc-apq8084.c | 1 - drivers/clk/qcom/gcc-ipq806x.c | 1 - drivers/clk/qcom/gcc-msm8660.c | 1 - drivers/clk/qcom/gcc-msm8916.c | 1 - drivers/clk/qcom/gcc-msm8960.c | 2 -- drivers/clk/qcom/gcc-msm8974.c | 1 - drivers/clk/qcom/lcc-ipq806x.c | 1 - drivers/clk/qcom/lcc-msm8960.c | 1 - drivers/clk/qcom/mmcc-apq8084.c | 1 - drivers/clk/qcom/mmcc-msm8960.c | 2 -- drivers/clk/qcom/mmcc-msm8974.c | 1 - 11 files changed, 13 deletions(-) diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c index cf73e539e9f6..070037a29ea5 100644 --- a/drivers/clk/qcom/gcc-apq8084.c +++ b/drivers/clk/qcom/gcc-apq8084.c @@ -3587,7 +3587,6 @@ static const struct regmap_config gcc_apq8084_regmap_config = { .val_bits = 32, .max_register = 0x1fc0, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc gcc_apq8084_desc = { diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c index b692ae881d6a..dd5402bac620 100644 --- a/drivers/clk/qcom/gcc-ipq806x.c +++ b/drivers/clk/qcom/gcc-ipq806x.c @@ -3005,7 +3005,6 @@ static const struct regmap_config gcc_ipq806x_regmap_config = { .val_bits = 32, .max_register = 0x3e40, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc gcc_ipq806x_desc = { diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c index f6a2b14dfec4..ad413036f7c7 100644 --- a/drivers/clk/qcom/gcc-msm8660.c +++ b/drivers/clk/qcom/gcc-msm8660.c @@ -2702,7 +2702,6 @@ static const struct regmap_config gcc_msm8660_regmap_config = { .val_bits = 32, .max_register = 0x363c, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc gcc_msm8660_desc = { diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c index e3bf09d7d0ef..8cc9b2868b41 100644 --- a/drivers/clk/qcom/gcc-msm8916.c +++ b/drivers/clk/qcom/gcc-msm8916.c @@ -3336,7 +3336,6 @@ static const struct regmap_config gcc_msm8916_regmap_config = { .val_bits = 32, .max_register = 0x80000, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc gcc_msm8916_desc = { diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c index f31111e32d44..983dd7dc89a7 100644 --- a/drivers/clk/qcom/gcc-msm8960.c +++ b/drivers/clk/qcom/gcc-msm8960.c @@ -3468,7 +3468,6 @@ static const struct regmap_config gcc_msm8960_regmap_config = { .val_bits = 32, .max_register = 0x3660, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct regmap_config gcc_apq8064_regmap_config = { @@ -3477,7 +3476,6 @@ static const struct regmap_config gcc_apq8064_regmap_config = { .val_bits = 32, .max_register = 0x3880, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc gcc_msm8960_desc = { diff --git a/drivers/clk/qcom/gcc-msm8974.c b/drivers/clk/qcom/gcc-msm8974.c index df164d618e34..335952db309b 100644 --- a/drivers/clk/qcom/gcc-msm8974.c +++ b/drivers/clk/qcom/gcc-msm8974.c @@ -2680,7 +2680,6 @@ static const struct regmap_config gcc_msm8974_regmap_config = { .val_bits = 32, .max_register = 0x1fc0, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc gcc_msm8974_desc = { diff --git a/drivers/clk/qcom/lcc-ipq806x.c b/drivers/clk/qcom/lcc-ipq806x.c index 62e79fadd5f7..db3998e5e2d8 100644 --- a/drivers/clk/qcom/lcc-ipq806x.c +++ b/drivers/clk/qcom/lcc-ipq806x.c @@ -419,7 +419,6 @@ static const struct regmap_config lcc_ipq806x_regmap_config = { .val_bits = 32, .max_register = 0xfc, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc lcc_ipq806x_desc = { diff --git a/drivers/clk/qcom/lcc-msm8960.c b/drivers/clk/qcom/lcc-msm8960.c index bf95bb0ea1b8..4fcf9d1d233c 100644 --- a/drivers/clk/qcom/lcc-msm8960.c +++ b/drivers/clk/qcom/lcc-msm8960.c @@ -524,7 +524,6 @@ static const struct regmap_config lcc_msm8960_regmap_config = { .val_bits = 32, .max_register = 0xfc, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc lcc_msm8960_desc = { diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c index 1e703fda8a0f..30777f9f1a43 100644 --- a/drivers/clk/qcom/mmcc-apq8084.c +++ b/drivers/clk/qcom/mmcc-apq8084.c @@ -3368,7 +3368,6 @@ static const struct regmap_config mmcc_apq8084_regmap_config = { .val_bits = 32, .max_register = 0x5104, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc mmcc_apq8084_desc = { diff --git a/drivers/clk/qcom/mmcc-msm8960.c b/drivers/clk/qcom/mmcc-msm8960.c index d73a048d3b9d..00e36192a1de 100644 --- a/drivers/clk/qcom/mmcc-msm8960.c +++ b/drivers/clk/qcom/mmcc-msm8960.c @@ -3029,7 +3029,6 @@ static const struct regmap_config mmcc_msm8960_regmap_config = { .val_bits = 32, .max_register = 0x334, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct regmap_config mmcc_apq8064_regmap_config = { @@ -3038,7 +3037,6 @@ static const struct regmap_config mmcc_apq8064_regmap_config = { .val_bits = 32, .max_register = 0x350, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc mmcc_msm8960_desc = { diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c index bbe28ed93669..9d790bcadf25 100644 --- a/drivers/clk/qcom/mmcc-msm8974.c +++ b/drivers/clk/qcom/mmcc-msm8974.c @@ -2594,7 +2594,6 @@ static const struct regmap_config mmcc_msm8974_regmap_config = { .val_bits = 32, .max_register = 0x5104, .fast_io = true, - .val_format_endian = REGMAP_ENDIAN_LITTLE, }; static const struct qcom_cc_desc mmcc_msm8974_desc = { From 21a75f0915dde8674708b39abfcda113911c49b1 Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Tue, 2 Feb 2016 13:35:56 -0800 Subject: [PATCH 118/489] bonding: Fix ARP monitor validation The current logic in bond_arp_rcv will accept an incoming ARP for validation if (a) the receiving slave is either "active" (which includes the currently active slave, or the current ARP slave) or, (b) there is a currently active slave, and it has received an ARP since it became active. For case (b), the receiving slave isn't the currently active slave, and is receiving the original broadcast ARP request, not an ARP reply from the target. This logic can fail if there is no currently active slave. In this situation, the ARP probe logic cycles through all slaves, assigning each in turn as the "current_arp_slave" for one arp_interval, then setting that one as "active," and sending an ARP probe from that slave. The current logic expects the ARP reply to arrive on the sending current_arp_slave, however, due to switch FDB updating delays, the reply may be directed to another slave. This can arise if the bonding slaves and switch are working, but the ARP target is not responding. When the ARP target recovers, a condition may result wherein the ARP target host replies faster than the switch can update its forwarding table, causing each ARP reply to be sent to the previous current_arp_slave. This will never pass the logic in bond_arp_rcv, as neither of the above conditions (a) or (b) are met. Some experimentation on a LAN shows ARP reply round trips in the 200 usec range, but my available switches never update their FDB in less than 4000 usec. This patch changes the logic in bond_arp_rcv to additionally accept an ARP reply for validation on any slave if there is a current ARP slave and it sent an ARP probe during the previous arp_interval. Fixes: aeea64ac717a ("bonding: don't trust arp requests unless active slave really works") Cc: Veaceslav Falico Cc: Andy Gospodarek Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 39 +++++++++++++++++++++++---------- 1 file changed, 28 insertions(+), 11 deletions(-) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 56b560558884..65a4107749df 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -214,6 +214,8 @@ static void bond_uninit(struct net_device *bond_dev); static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats); static void bond_slave_arr_handler(struct work_struct *work); +static bool bond_time_in_interval(struct bonding *bond, unsigned long last_act, + int mod); /*---------------------------- General routines -----------------------------*/ @@ -2459,7 +2461,7 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, struct slave *slave) { struct arphdr *arp = (struct arphdr *)skb->data; - struct slave *curr_active_slave; + struct slave *curr_active_slave, *curr_arp_slave; unsigned char *arp_ptr; __be32 sip, tip; int alen, is_arp = skb->protocol == __cpu_to_be16(ETH_P_ARP); @@ -2506,26 +2508,41 @@ int bond_arp_rcv(const struct sk_buff *skb, struct bonding *bond, &sip, &tip); curr_active_slave = rcu_dereference(bond->curr_active_slave); + curr_arp_slave = rcu_dereference(bond->current_arp_slave); - /* Backup slaves won't see the ARP reply, but do come through - * here for each ARP probe (so we swap the sip/tip to validate - * the probe). In a "redundant switch, common router" type of - * configuration, the ARP probe will (hopefully) travel from - * the active, through one switch, the router, then the other - * switch before reaching the backup. + /* We 'trust' the received ARP enough to validate it if: * - * We 'trust' the arp requests if there is an active slave and - * it received valid arp reply(s) after it became active. This - * is done to avoid endless looping when we can't reach the + * (a) the slave receiving the ARP is active (which includes the + * current ARP slave, if any), or + * + * (b) the receiving slave isn't active, but there is a currently + * active slave and it received valid arp reply(s) after it became + * the currently active slave, or + * + * (c) there is an ARP slave that sent an ARP during the prior ARP + * interval, and we receive an ARP reply on any slave. We accept + * these because switch FDB update delays may deliver the ARP + * reply to a slave other than the sender of the ARP request. + * + * Note: for (b), backup slaves are receiving the broadcast ARP + * request, not a reply. This request passes from the sending + * slave through the L2 switch(es) to the receiving slave. Since + * this is checking the request, sip/tip are swapped for + * validation. + * + * This is done to avoid endless looping when we can't reach the * arp_ip_target and fool ourselves with our own arp requests. */ - if (bond_is_active_slave(slave)) bond_validate_arp(bond, slave, sip, tip); else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) bond_validate_arp(bond, slave, tip, sip); + else if (curr_arp_slave && (arp->ar_op == htons(ARPOP_REPLY)) && + bond_time_in_interval(bond, + dev_trans_start(curr_arp_slave->dev), 1)) + bond_validate_arp(bond, slave, sip, tip); out_unlock: if (arp != (struct arphdr *)skb->data) From 08a965ec93ad0495802462c32b73241d658e189d Mon Sep 17 00:00:00 2001 From: Amitoj Kaur Chawla Date: Thu, 4 Feb 2016 19:25:13 +0530 Subject: [PATCH 119/489] net: cavium: liquidio: Return correct error code The return value of vmalloc on failure of allocation of memory should be -ENOMEM and not -1. Found using Coccinelle. A simplified version of the semantic patch used is: // @@ expression *e; identifier l1; position p,q; @@ e@q = vmalloc(...); if@p (e == NULL) { ... goto l1; } l1: ... return -1 + -ENOMEM ; // Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- drivers/net/ethernet/cavium/liquidio/octeon_droq.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 872765527081..ac0394c9e8ab 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1683,7 +1683,7 @@ static int octeon_setup_droq(struct octeon_device *oct, int q_no, int num_descs, dev_dbg(&oct->pci_dev->dev, "Creating Droq: %d\n", q_no); /* droq creation and local register settings. */ ret_val = octeon_create_droq(oct, q_no, num_descs, desc_size, app_ctx); - if (ret_val == -1) + if (ret_val < 0) return ret_val; if (ret_val == 1) { diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index 4dba86eaa045..174072b3740b 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -983,5 +983,5 @@ int octeon_create_droq(struct octeon_device *oct, create_droq_fail: octeon_delete_droq(oct, q_no); - return -1; + return -ENOMEM; } From c2bb7bc5c007b7b55087eb05409edc2014f43ca8 Mon Sep 17 00:00:00 2001 From: Amitoj Kaur Chawla Date: Thu, 4 Feb 2016 19:25:26 +0530 Subject: [PATCH 120/489] net: mvpp2: Return correct error codes The return value of kzalloc on failure of allocation of memory should be -ENOMEM and not -1. Found using Coccinelle. A simplified version of the semantic patch used is: // @@ expression *e; position p,q; @@ e@q = kzalloc(...); if@p (e == NULL) { ... return - -1 + -ENOMEM ; } // This function may also return -1 after calling mpp2_prs_tcam_port_map_get. So that the function consistently returns meaningful error values on failure, the -1 is changed to -EINVAL. Signed-off-by: Amitoj Kaur Chawla Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvpp2.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c index a4beccf1fd46..c797971aefab 100644 --- a/drivers/net/ethernet/marvell/mvpp2.c +++ b/drivers/net/ethernet/marvell/mvpp2.c @@ -3061,7 +3061,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port, pe = kzalloc(sizeof(*pe), GFP_KERNEL); if (!pe) - return -1; + return -ENOMEM; mvpp2_prs_tcam_lu_set(pe, MVPP2_PRS_LU_MAC); pe->index = tid; @@ -3077,7 +3077,7 @@ static int mvpp2_prs_mac_da_accept(struct mvpp2 *priv, int port, if (pmap == 0) { if (add) { kfree(pe); - return -1; + return -EINVAL; } mvpp2_prs_hw_inv(priv, pe->index); priv->prs_shadow[pe->index].valid = false; From 919483096bfe75dda338e98d56da91a263746a0a Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 4 Feb 2016 06:23:28 -0800 Subject: [PATCH 121/489] ipv4: fix memory leaks in ip_cmsg_send() callers Dmitry reported memory leaks of IP options allocated in ip_cmsg_send() when/if this function returns an error. Callers are responsible for the freeing. Many thanks to Dmitry for the report and diagnostic. Reported-by: Dmitry Vyukov Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/ip_sockglue.c | 2 ++ net/ipv4/ping.c | 4 +++- net/ipv4/raw.c | 4 +++- net/ipv4/udp.c | 4 +++- 4 files changed, 11 insertions(+), 3 deletions(-) diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 5f73a7c03e27..a50124260f5a 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc, switch (cmsg->cmsg_type) { case IP_RETOPTS: err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)); + + /* Our caller is responsible for freeing ipc->opt */ err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg), err < 40 ? err : 40); if (err) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index c117b21b937d..d3a27165f9cc 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index bc35f1842512..7113bae4e6a0 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(net, msg, &ipc, false); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); goto out; + } if (ipc.opt) free = 1; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index be0b21852b13..95d2f198017e 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1048,8 +1048,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = ip_cmsg_send(sock_net(sk), msg, &ipc, sk->sk_family == AF_INET6); - if (err) + if (unlikely(err)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; connected = 0; From a2cb7ec001559d649b09572a7a5e4f69222eb467 Mon Sep 17 00:00:00 2001 From: Chun-Hao Lin Date: Fri, 5 Feb 2016 02:28:00 +0800 Subject: [PATCH 122/489] r8169:fix system hange problem. There are typos in setting RTL8168H hardware parameters. If system install another version driver that may cuase system hang. Signed-off-by: Chunhao Lin Signed-off-by: David S. Miller --- drivers/net/ethernet/realtek/r8169.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 17d5571d0432..537974cfd427 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -6137,28 +6137,28 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) sw_cnt_1ms_ini = 16000000/rg_saw_cnt; sw_cnt_1ms_ini &= 0x0fff; data = r8168_mac_ocp_read(tp, 0xd412); - data &= 0x0fff; + data &= ~0x0fff; data |= sw_cnt_1ms_ini; r8168_mac_ocp_write(tp, 0xd412, data); } data = r8168_mac_ocp_read(tp, 0xe056); - data &= 0xf0; - data |= 0x07; + data &= ~0xf0; + data |= 0x70; r8168_mac_ocp_write(tp, 0xe056, data); data = r8168_mac_ocp_read(tp, 0xe052); - data &= 0x8008; - data |= 0x6000; + data &= ~0x6000; + data |= 0x8008; r8168_mac_ocp_write(tp, 0xe052, data); data = r8168_mac_ocp_read(tp, 0xe0d6); - data &= 0x01ff; + data &= ~0x01ff; data |= 0x017f; r8168_mac_ocp_write(tp, 0xe0d6, data); data = r8168_mac_ocp_read(tp, 0xd420); - data &= 0x0fff; + data &= ~0x0fff; data |= 0x047f; r8168_mac_ocp_write(tp, 0xd420, data); From 5988818008257ca42010d6b43a3e0e48afec9898 Mon Sep 17 00:00:00 2001 From: Laura Abbott Date: Thu, 4 Feb 2016 10:50:45 -0800 Subject: [PATCH 123/489] vsock: Fix blocking ops call in prepare_to_wait We receoved a bug report from someone using vmware: WARNING: CPU: 3 PID: 660 at kernel/sched/core.c:7389 __might_sleep+0x7d/0x90() do not call blocking ops when !TASK_RUNNING; state=1 set at [] prepare_to_wait+0x2d/0x90 Modules linked in: vmw_vsock_vmci_transport vsock snd_seq_midi snd_seq_midi_event snd_ens1371 iosf_mbi gameport snd_rawmidi snd_ac97_codec ac97_bus snd_seq coretemp snd_seq_device snd_pcm snd_timer snd soundcore ppdev crct10dif_pclmul crc32_pclmul ghash_clmulni_intel vmw_vmci vmw_balloon i2c_piix4 shpchp parport_pc parport acpi_cpufreq nfsd auth_rpcgss nfs_acl lockd grace sunrpc btrfs xor raid6_pq 8021q garp stp llc mrp crc32c_intel serio_raw mptspi vmwgfx drm_kms_helper ttm drm scsi_transport_spi mptscsih e1000 ata_generic mptbase pata_acpi CPU: 3 PID: 660 Comm: vmtoolsd Not tainted 4.2.0-0.rc1.git3.1.fc23.x86_64 #1 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 05/20/2014 0000000000000000 0000000049e617f3 ffff88006ac37ac8 ffffffff818641f5 0000000000000000 ffff88006ac37b20 ffff88006ac37b08 ffffffff810ab446 ffff880068009f40 ffffffff81c63bc0 0000000000000061 0000000000000000 Call Trace: [] dump_stack+0x4c/0x65 [] warn_slowpath_common+0x86/0xc0 [] warn_slowpath_fmt+0x55/0x70 [] ? debug_lockdep_rcu_enabled+0x1d/0x20 [] ? prepare_to_wait+0x2d/0x90 [] ? prepare_to_wait+0x2d/0x90 [] __might_sleep+0x7d/0x90 [] __might_fault+0x43/0xa0 [] copy_from_iter+0x87/0x2a0 [] __qp_memcpy_to_queue+0x9a/0x1b0 [vmw_vmci] [] ? qp_memcpy_to_queue+0x20/0x20 [vmw_vmci] [] qp_memcpy_to_queue_iov+0x17/0x20 [vmw_vmci] [] qp_enqueue_locked+0xa0/0x140 [vmw_vmci] [] vmci_qpair_enquev+0x4f/0xd0 [vmw_vmci] [] vmci_transport_stream_enqueue+0x1b/0x20 [vmw_vsock_vmci_transport] [] vsock_stream_sendmsg+0x2c5/0x320 [vsock] [] ? wake_atomic_t_function+0x70/0x70 [] sock_sendmsg+0x38/0x50 [] SYSC_sendto+0x104/0x190 [] ? vfs_read+0x8a/0x140 [] SyS_sendto+0xe/0x10 [] entry_SYSCALL_64_fastpath+0x12/0x76 transport->stream_enqueue may call copy_to_user so it should not be called inside a prepare_to_wait. Narrow the scope of the prepare_to_wait to avoid the bad call. This also applies to vsock_stream_recvmsg as well. Reported-by: Vinson Lee Tested-by: Vinson Lee Signed-off-by: Laura Abbott Signed-off-by: David S. Miller --- net/vmw_vsock/af_vsock.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-) diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 7fd1220fbfa0..bbe65dcb9738 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1557,8 +1557,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - while (total_written < len) { ssize_t written; @@ -1578,7 +1576,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; release_sock(sk); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { err = sock_intr_errno(timeout); @@ -1588,8 +1588,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, goto out_wait; } - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } /* These checks occur both as part of and after the loop @@ -1635,7 +1633,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, out_wait: if (total_written > 0) err = total_written; - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; @@ -1716,7 +1713,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (err < 0) goto out; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); while (1) { s64 ready = vsock_stream_has_data(vsk); @@ -1727,7 +1723,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, */ err = -ENOMEM; - goto out_wait; + goto out; } else if (ready > 0) { ssize_t read; @@ -1750,7 +1746,7 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, vsk, target, read, !(flags & MSG_PEEK), &recv_data); if (err < 0) - goto out_wait; + goto out; if (read >= target || flags & MSG_PEEK) break; @@ -1773,7 +1769,9 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, break; release_sock(sk); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); timeout = schedule_timeout(timeout); + finish_wait(sk_sleep(sk), &wait); lock_sock(sk); if (signal_pending(current)) { @@ -1783,9 +1781,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = -EAGAIN; break; } - - prepare_to_wait(sk_sleep(sk), &wait, - TASK_INTERRUPTIBLE); } } @@ -1816,8 +1811,6 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, err = copied; } -out_wait: - finish_wait(sk_sleep(sk), &wait); out: release_sock(sk); return err; From 129219e4950a3fcf9323b3bbd8b224c7aa873985 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:23 +0100 Subject: [PATCH 124/489] net: mvneta: Fix for_each_present_cpu usage This patch convert the for_each_present in on_each_cpu, instead of applying on the present cpus it will be applied only on the online cpus. This fix a bug reported on http://thread.gmane.org/gmane.linux.ports.arm.kernel/468173. Using the macro on_each_cpu (instead of a for_each_* loop) also ensures that all the calls will be done all at once. Fixes: f86428854480 ("net: mvneta: Statically assign queues to CPUs") Reported-by: Stefan Roese Suggested-by: Jisheng Zhang Suggested-by: Russell King Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 662c2ee268c7..90ff5c7e19ea 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2564,7 +2564,7 @@ static void mvneta_start_dev(struct mvneta_port *pp) mvneta_port_enable(pp); /* Enable polling on the port */ - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); napi_enable(&port->napi); @@ -2589,7 +2589,7 @@ static void mvneta_stop_dev(struct mvneta_port *pp) phy_stop(pp->phy_dev); - for_each_present_cpu(cpu) { + for_each_online_cpu(cpu) { struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu); napi_disable(&port->napi); @@ -3057,13 +3057,11 @@ err_cleanup_rxqs: static int mvneta_stop(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); - int cpu; mvneta_stop_dev(pp); mvneta_mdio_remove(pp); unregister_cpu_notifier(&pp->cpu_notifier); - for_each_present_cpu(cpu) - smp_call_function_single(cpu, mvneta_percpu_disable, pp, true); + on_each_cpu(mvneta_percpu_disable, pp, true); free_percpu_irq(dev->irq, pp->ports); mvneta_cleanup_rxqs(pp); mvneta_cleanup_txqs(pp); From cad5d847a093077b499a8b0bbfe6804b9226c03e Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:24 +0100 Subject: [PATCH 125/489] net: mvneta: Fix the CPU choice in mvneta_percpu_elect When passing to the management of multiple RX queue, the mvneta_percpu_elect function was broken. The use of the modulo can lead to elect the wrong cpu. For example with rxq_def=2, if the CPU 2 goes offline and then online, we ended with the third RX queue activated in the same time on CPU 0 and CPU2, which lead to a kernel crash. With this fix, we don't try to get "the closer" CPU if the default CPU is gone, now we just use CPU 0 which always be there. Thanks to this, the code becomes more readable, easier to maintain and more predicable. Cc: stable@vger.kernel.org Fixes: 2dcf75e2793c ("net: mvneta: Associate RX queues with each CPU") Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 90ff5c7e19ea..4c2d12423750 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2849,9 +2849,14 @@ static void mvneta_percpu_disable(void *arg) static void mvneta_percpu_elect(struct mvneta_port *pp) { - int online_cpu_idx, max_cpu, cpu, i = 0; + int elected_cpu = 0, max_cpu, cpu, i = 0; + + /* Use the cpu associated to the rxq when it is online, in all + * the other cases, use the cpu 0 which can't be offline. + */ + if (cpu_online(pp->rxq_def)) + elected_cpu = pp->rxq_def; - online_cpu_idx = pp->rxq_def % num_online_cpus(); max_cpu = num_present_cpus(); for_each_online_cpu(cpu) { @@ -2862,7 +2867,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) if ((rxq % max_cpu) == cpu) rxq_map |= MVNETA_CPU_RXQ_ACCESS(rxq); - if (i == online_cpu_idx) + if (cpu == elected_cpu) /* Map the default receive queue queue to the * elected CPU */ @@ -2873,7 +2878,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) * the CPU bound to the default RX queue */ if (txq_number == 1) - txq_map = (i == online_cpu_idx) ? + txq_map = (cpu == elected_cpu) ? MVNETA_CPU_TXQ_ACCESS(1) : 0; else txq_map = mvreg_read(pp, MVNETA_CPU_MAP(cpu)) & From 6b125d63b7f6c30d36dad3d999bbb5d44f359ebd Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:25 +0100 Subject: [PATCH 126/489] net: mvneta: Use on_each_cpu when possible Instead of using a for_each_* loop in which we just call the smp_call_function_single macro, it is more simple to directly use the on_each_cpu macro. Moreover, this macro ensures that the calls will be done all at once. Suggested-by: Russell King Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 4c2d12423750..f496f9716569 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2555,7 +2555,7 @@ static void mvneta_percpu_mask_interrupt(void *arg) static void mvneta_start_dev(struct mvneta_port *pp) { - unsigned int cpu; + int cpu; mvneta_max_rx_size_set(pp, pp->pkt_size); mvneta_txq_max_tx_size_set(pp, pp->pkt_size); @@ -2571,9 +2571,8 @@ static void mvneta_start_dev(struct mvneta_port *pp) } /* Unmask interrupts. It has to be done from each CPU */ - for_each_online_cpu(cpu) - smp_call_function_single(cpu, mvneta_percpu_unmask_interrupt, - pp, true); + on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, MVNETA_CAUSE_PHY_STATUS_CHANGE | MVNETA_CAUSE_LINK_CHANGE | @@ -2993,7 +2992,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, static int mvneta_open(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); - int ret, cpu; + int ret; pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) + @@ -3026,9 +3025,7 @@ static int mvneta_open(struct net_device *dev) /* Enable per-CPU interrupt on all the CPU to handle our RX * queue interrupts */ - for_each_online_cpu(cpu) - smp_call_function_single(cpu, mvneta_percpu_enable, - pp, true); + on_each_cpu(mvneta_percpu_enable, pp, true); /* Register a CPU notifier to handle the case where our CPU @@ -3315,9 +3312,7 @@ static int mvneta_config_rss(struct mvneta_port *pp) netif_tx_stop_all_queues(pp->dev); - for_each_online_cpu(cpu) - smp_call_function_single(cpu, mvneta_percpu_mask_interrupt, - pp, true); + on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); /* We have to synchronise on the napi of each CPU */ for_each_online_cpu(cpu) { From cde4c0fec4e223727c24c2cd7e88ece57b48b70e Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:26 +0100 Subject: [PATCH 127/489] net: mvneta: Remove unused code Since the commit 2dcf75e2793c ("net: mvneta: Associate RX queues with each CPU") all the percpu irq are used and disabled at initialization, so there is no point to disable them first. Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index f496f9716569..74f8158df2b0 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3014,14 +3014,6 @@ static int mvneta_open(struct net_device *dev) goto err_cleanup_txqs; } - /* Even though the documentation says that request_percpu_irq - * doesn't enable the interrupts automatically, it actually - * does so on the local CPU. - * - * Make sure it's disabled. - */ - mvneta_percpu_disable(pp); - /* Enable per-CPU interrupt on all the CPU to handle our RX * queue interrupts */ From db488c10f2a00dbd417b158db2b551e5e262e957 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:27 +0100 Subject: [PATCH 128/489] net: mvneta: Modify the queue related fields from each cpu In the MVNETA_INTR_* registers, the queues related fields are per cpu, according to the datasheet (comment in [] are added by me): "In a multi-CPU system, bits of RX[or TX] queues for which the access by the reading[or writing] CPU is disabled are read as 0, and cannot be cleared[or written]." That means that each time we want to manipulate these bits we had to do it on each cpu and not only on the current cpu. Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 100 ++++++++++++-------------- 1 file changed, 46 insertions(+), 54 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 74f8158df2b0..2d0e8a605ca9 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -1038,6 +1038,43 @@ static void mvneta_set_autoneg(struct mvneta_port *pp, int enable) } } +static void mvneta_percpu_unmask_interrupt(void *arg) +{ + struct mvneta_port *pp = arg; + + /* All the queue are unmasked, but actually only the ones + * mapped to this CPU will be unmasked + */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, + MVNETA_RX_INTR_MASK_ALL | + MVNETA_TX_INTR_MASK_ALL | + MVNETA_MISCINTR_INTR_MASK); +} + +static void mvneta_percpu_mask_interrupt(void *arg) +{ + struct mvneta_port *pp = arg; + + /* All the queue are masked, but actually only the ones + * mapped to this CPU will be masked + */ + mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); + mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); + mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); +} + +static void mvneta_percpu_clear_intr_cause(void *arg) +{ + struct mvneta_port *pp = arg; + + /* All the queue are cleared, but actually only the ones + * mapped to this CPU will be cleared + */ + mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0); + mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0); + mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0); +} + /* This method sets defaults to the NETA port: * Clears interrupt Cause and Mask registers. * Clears all MAC tables. @@ -1055,14 +1092,10 @@ static void mvneta_defaults_set(struct mvneta_port *pp) int max_cpu = num_present_cpus(); /* Clear all Cause registers */ - mvreg_write(pp, MVNETA_INTR_NEW_CAUSE, 0); - mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0); - mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0); + on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true); /* Mask all interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); - mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); - mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); + on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); mvreg_write(pp, MVNETA_INTR_ENABLE, 0); /* Enable MBUS Retry bit16 */ @@ -2528,31 +2561,6 @@ static int mvneta_setup_txqs(struct mvneta_port *pp) return 0; } -static void mvneta_percpu_unmask_interrupt(void *arg) -{ - struct mvneta_port *pp = arg; - - /* All the queue are unmasked, but actually only the ones - * maped to this CPU will be unmasked - */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK_ALL | - MVNETA_TX_INTR_MASK_ALL | - MVNETA_MISCINTR_INTR_MASK); -} - -static void mvneta_percpu_mask_interrupt(void *arg) -{ - struct mvneta_port *pp = arg; - - /* All the queue are masked, but actually only the ones - * maped to this CPU will be masked - */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); - mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); - mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); -} - static void mvneta_start_dev(struct mvneta_port *pp) { int cpu; @@ -2603,13 +2611,10 @@ static void mvneta_stop_dev(struct mvneta_port *pp) mvneta_port_disable(pp); /* Clear all ethernet port interrupts */ - mvreg_write(pp, MVNETA_INTR_MISC_CAUSE, 0); - mvreg_write(pp, MVNETA_INTR_OLD_CAUSE, 0); + on_each_cpu(mvneta_percpu_clear_intr_cause, pp, true); /* Mask all ethernet port interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); - mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); - mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); + on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); mvneta_tx_reset(pp); mvneta_rx_reset(pp); @@ -2921,9 +2926,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, } /* Mask all ethernet port interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); - mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); - mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); + on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); napi_enable(&port->napi); @@ -2938,14 +2941,8 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, */ mvneta_percpu_elect(pp); - /* Unmask all ethernet port interrupts, as this - * notifier is called for each CPU then the CPU to - * Queue mapping is applied - */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK(rxq_number) | - MVNETA_TX_INTR_MASK(txq_number) | - MVNETA_MISCINTR_INTR_MASK); + /* Unmask all ethernet port interrupts */ + on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true); mvreg_write(pp, MVNETA_INTR_MISC_MASK, MVNETA_CAUSE_PHY_STATUS_CHANGE | MVNETA_CAUSE_LINK_CHANGE | @@ -2956,9 +2953,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, case CPU_DOWN_PREPARE_FROZEN: netif_tx_stop_all_queues(pp->dev); /* Mask all ethernet port interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, 0); - mvreg_write(pp, MVNETA_INTR_OLD_MASK, 0); - mvreg_write(pp, MVNETA_INTR_MISC_MASK, 0); + on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); napi_synchronize(&port->napi); napi_disable(&port->napi); @@ -2974,10 +2969,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, /* Check if a new CPU must be elected now this on is down */ mvneta_percpu_elect(pp); /* Unmask all ethernet port interrupts */ - mvreg_write(pp, MVNETA_INTR_NEW_MASK, - MVNETA_RX_INTR_MASK(rxq_number) | - MVNETA_TX_INTR_MASK(txq_number) | - MVNETA_MISCINTR_INTR_MASK); + on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true); mvreg_write(pp, MVNETA_INTR_MISC_MASK, MVNETA_CAUSE_PHY_STATUS_CHANGE | MVNETA_CAUSE_LINK_CHANGE | From 5888511ea053fa8d6019252ad333e8a7cb7f9475 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:28 +0100 Subject: [PATCH 129/489] net: mvneta: The mvneta_percpu_elect function should be atomic Electing a CPU must be done in an atomic way: it should be done after or before the removal/insertion of a CPU and this function is not reentrant. During the loop of mvneta_percpu_elect we associates the queues to the CPUs, if there is a topology change during this loop, then the mapping between the CPUs and the queues could be wrong. During this loop the interrupt mask is also updating for each CPUs, It should not be changed in the same time by other part of the driver. This patch adds spinlock to create the needed critical sections. Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 2d0e8a605ca9..b12a745a0e4c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -370,6 +370,10 @@ struct mvneta_port { struct net_device *dev; struct notifier_block cpu_notifier; int rxq_def; + /* Protect the access to the percpu interrupt registers, + * ensuring that the configuration remains coherent. + */ + spinlock_t lock; /* Core clock */ struct clk *clk; @@ -2855,6 +2859,12 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) { int elected_cpu = 0, max_cpu, cpu, i = 0; + /* Electing a CPU must be done in an atomic way: it should be + * done after or before the removal/insertion of a CPU and + * this function is not reentrant. + */ + spin_lock(&pp->lock); + /* Use the cpu associated to the rxq when it is online, in all * the other cases, use the cpu 0 which can't be offline. */ @@ -2898,6 +2908,7 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) i++; } + spin_unlock(&pp->lock); }; static int mvneta_percpu_notifier(struct notifier_block *nfb, @@ -2952,8 +2963,13 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: netif_tx_stop_all_queues(pp->dev); + /* Thanks to this lock we are sure that any pending + * cpu election is done + */ + spin_lock(&pp->lock); /* Mask all ethernet port interrupts */ on_each_cpu(mvneta_percpu_mask_interrupt, pp, true); + spin_unlock(&pp->lock); napi_synchronize(&port->napi); napi_disable(&port->napi); From 120cfa502c7763f4a3758b9601f2c13d33083d64 Mon Sep 17 00:00:00 2001 From: Gregory CLEMENT Date: Thu, 4 Feb 2016 22:09:29 +0100 Subject: [PATCH 130/489] net: mvneta: Fix race condition during stopping When stopping the port, the CPU notifier are still there whereas the mvneta_stop_dev function calls mvneta_percpu_disable() on each CPUs. It was possible to have a new CPU coming at this point which could be racy. This patch adds a flag preventing executing the code notifier for a new CPU when the port is stopping. It also uses the spinlock introduces previously. To avoid the deadlock, the lock has been moved outside the mvneta_percpu_elect function. Signed-off-by: Gregory CLEMENT Signed-off-by: David S. Miller --- drivers/net/ethernet/marvell/mvneta.c | 36 +++++++++++++++++++++------ 1 file changed, 28 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index b12a745a0e4c..b0ae69f84493 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -374,6 +374,7 @@ struct mvneta_port { * ensuring that the configuration remains coherent. */ spinlock_t lock; + bool is_stopped; /* Core clock */ struct clk *clk; @@ -2855,16 +2856,14 @@ static void mvneta_percpu_disable(void *arg) disable_percpu_irq(pp->dev->irq); } +/* Electing a CPU must be done in an atomic way: it should be done + * after or before the removal/insertion of a CPU and this function is + * not reentrant. + */ static void mvneta_percpu_elect(struct mvneta_port *pp) { int elected_cpu = 0, max_cpu, cpu, i = 0; - /* Electing a CPU must be done in an atomic way: it should be - * done after or before the removal/insertion of a CPU and - * this function is not reentrant. - */ - spin_lock(&pp->lock); - /* Use the cpu associated to the rxq when it is online, in all * the other cases, use the cpu 0 which can't be offline. */ @@ -2908,7 +2907,6 @@ static void mvneta_percpu_elect(struct mvneta_port *pp) i++; } - spin_unlock(&pp->lock); }; static int mvneta_percpu_notifier(struct notifier_block *nfb, @@ -2922,6 +2920,14 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: + spin_lock(&pp->lock); + /* Configuring the driver for a new CPU while the + * driver is stopping is racy, so just avoid it. + */ + if (pp->is_stopped) { + spin_unlock(&pp->lock); + break; + } netif_tx_stop_all_queues(pp->dev); /* We have to synchronise on tha napi of each CPU @@ -2959,6 +2965,7 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, MVNETA_CAUSE_LINK_CHANGE | MVNETA_CAUSE_PSC_SYNC_CHANGE); netif_tx_start_all_queues(pp->dev); + spin_unlock(&pp->lock); break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: @@ -2983,7 +2990,9 @@ static int mvneta_percpu_notifier(struct notifier_block *nfb, case CPU_DEAD: case CPU_DEAD_FROZEN: /* Check if a new CPU must be elected now this on is down */ + spin_lock(&pp->lock); mvneta_percpu_elect(pp); + spin_unlock(&pp->lock); /* Unmask all ethernet port interrupts */ on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true); mvreg_write(pp, MVNETA_INTR_MISC_MASK, @@ -3027,7 +3036,7 @@ static int mvneta_open(struct net_device *dev) */ on_each_cpu(mvneta_percpu_enable, pp, true); - + pp->is_stopped = false; /* Register a CPU notifier to handle the case where our CPU * might be taken offline. */ @@ -3060,9 +3069,18 @@ static int mvneta_stop(struct net_device *dev) { struct mvneta_port *pp = netdev_priv(dev); + /* Inform that we are stopping so we don't want to setup the + * driver for new CPUs in the notifiers + */ + spin_lock(&pp->lock); + pp->is_stopped = true; mvneta_stop_dev(pp); mvneta_mdio_remove(pp); unregister_cpu_notifier(&pp->cpu_notifier); + /* Now that the notifier are unregistered, we can release le + * lock + */ + spin_unlock(&pp->lock); on_each_cpu(mvneta_percpu_disable, pp, true); free_percpu_irq(dev->irq, pp->ports); mvneta_cleanup_rxqs(pp); @@ -3333,7 +3351,9 @@ static int mvneta_config_rss(struct mvneta_port *pp) mvreg_write(pp, MVNETA_PORT_CONFIG, val); /* Update the elected CPU matching the new rxq_def */ + spin_lock(&pp->lock); mvneta_percpu_elect(pp); + spin_unlock(&pp->lock); /* We have to synchronise on the napi of each CPU */ for_each_online_cpu(cpu) { From 14a03cf80edf3e19953bb744938e48bc9d496d30 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Fri, 5 Feb 2016 17:29:08 +0100 Subject: [PATCH 131/489] hv_netvsc: Restore needed_headroom request Commit c0eb454034aa ("hv_netvsc: Don't ask for additional head room in the skb") got rid of needed_headroom setting for the driver. With the change I hit the following issue trying to use ptkgen module: [ 57.522021] kernel BUG at net/core/skbuff.c:1128! [ 57.522021] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC ... [ 58.721068] Call Trace: [ 58.721068] [] netvsc_start_xmit+0x4c6/0x8e0 [hv_netvsc] ... [ 58.721068] [] ? pktgen_finalize_skb+0x25c/0x2a0 [pktgen] [ 58.721068] [] ? __netdev_alloc_skb+0xc0/0x100 [ 58.721068] [] pktgen_thread_worker+0x257/0x1920 [pktgen] Basically, we're calling skb_cow_head(skb, RNDIS_AND_PPI_SIZE) and crash on if (skb_shared(skb)) BUG(); We probably need to restore needed_headroom setting (but shrunk to RNDIS_AND_PPI_SIZE as we don't need more) to request the required headroom space. In theory, it should not give us performance penalty. Signed-off-by: Vitaly Kuznetsov Signed-off-by: David S. Miller --- drivers/net/hyperv/netvsc_drv.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 1d3a66563bac..98e34fee45c7 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1089,6 +1089,9 @@ static int netvsc_probe(struct hv_device *dev, net->ethtool_ops = ðtool_ops; SET_NETDEV_DEV(net, &dev->device); + /* We always need headroom for rndis header */ + net->needed_headroom = RNDIS_AND_PPI_SIZE; + /* Notify the netvsc driver of the new device */ memset(&device_info, 0, sizeof(device_info)); device_info.ring_size = ring_size; From 19a6d156a7bd080f3a855a40a4a08ab475e34b4a Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 5 Feb 2016 16:30:39 +0000 Subject: [PATCH 132/489] net: cavium: liquidio: fix check for in progress flag smatch detected a suspicious looking bitop condition: drivers/net/ethernet/cavium/liquidio/lio_main.c:2529 handle_timestamp() warn: suspicious bitop condition (skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS is always non-zero, so the logic is definitely not correct. Use & to mask the correct bit. Signed-off-by: Colin Ian King Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/liquidio/lio_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index ac0394c9e8ab..34d269cd5579 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2524,7 +2524,7 @@ static void handle_timestamp(struct octeon_device *oct, octeon_swap_8B_data(&resp->timestamp, 1); - if (unlikely((skb_shinfo(skb)->tx_flags | SKBTX_IN_PROGRESS) != 0)) { + if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) != 0)) { struct skb_shared_hwtstamps ts; u64 ns = resp->timestamp; From 3c06f08b657205489d408ee7cbbcbbb1d8a6bf85 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 5 Feb 2016 14:04:39 -0500 Subject: [PATCH 133/489] net: dsa: mv88e6xxx: fix software VLAN deletion The current bridge code calls switchdev_port_obj_del on a VLAN port even if the corresponding switchdev_port_obj_add call returned -EOPNOTSUPP. If the DSA driver doesn't return -EOPNOTSUPP for a software port VLAN in its port_vlan_del function, the VLAN is not deleted. Unbridging the port also generates a stack trace for the same reason. This can be quickly tested on a VLAN filtering enabled system with: # brctl addbr br0 # brctl addif br0 lan0 # brctl addbr br1 # brctl addif br1 lan1 # brctl delif br1 lan1 Both bridges have a default default_pvid set to 1. lan0 uses the hardware VLAN 1 while lan1 falls back to the software VLAN 1. Unbridging lan1 does not delete its software VLAN, and thus generates the following stack trace: [ 2991.681705] device lan1 left promiscuous mode [ 2991.686237] br1: port 1(lan1) entered disabled state [ 2991.725094] ------------[ cut here ]------------ [ 2991.729761] WARNING: CPU: 0 PID: 869 at net/bridge/br_vlan.c:314 __vlan_group_free+0x4c/0x50() [ 2991.738437] Modules linked in: [ 2991.741546] CPU: 0 PID: 869 Comm: ip Not tainted 4.4.0 #16 [ 2991.747039] Hardware name: Freescale Vybrid VF5xx/VF6xx (Device Tree) [ 2991.753511] Backtrace: [ 2991.756008] [<80014450>] (dump_backtrace) from [<8001469c>] (show_stack+0x20/0x24) [ 2991.763604] r6:80512644 r5:00000009 r4:00000000 r3:00000000 [ 2991.769343] [<8001467c>] (show_stack) from [<80268e44>] (dump_stack+0x24/0x28) [ 2991.776618] [<80268e20>] (dump_stack) from [<80025568>] (warn_slowpath_common+0x98/0xc4) [ 2991.784750] [<800254d0>] (warn_slowpath_common) from [<80025650>] (warn_slowpath_null+0x2c/0x34) [ 2991.793557] r8:00000000 r7:9f786a8c r6:9f76c440 r5:9f786a00 r4:9f68ac00 [ 2991.800366] [<80025624>] (warn_slowpath_null) from [<80512644>] (__vlan_group_free+0x4c/0x50) [ 2991.808946] [<805125f8>] (__vlan_group_free) from [<80514488>] (nbp_vlan_flush+0x44/0x68) [ 2991.817147] r4:9f68ac00 r3:9ec70000 [ 2991.820772] [<80514444>] (nbp_vlan_flush) from [<80506f08>] (del_nbp+0xac/0x130) [ 2991.828201] r5:9f56f800 r4:9f786a00 [ 2991.831841] [<80506e5c>] (del_nbp) from [<8050774c>] (br_del_if+0x40/0xbc) [ 2991.838724] r7:80590f68 r6:00000000 r5:9ec71c38 r4:9f76c440 [ 2991.844475] [<8050770c>] (br_del_if) from [<80503dc0>] (br_del_slave+0x1c/0x20) [ 2991.851802] r5:9ec71c38 r4:9f56f800 [ 2991.855428] [<80503da4>] (br_del_slave) from [<80484a34>] (do_setlink+0x324/0x7b8) [ 2991.863043] [<80484710>] (do_setlink) from [<80485e90>] (rtnl_newlink+0x508/0x6f4) [ 2991.870616] r10:00000000 r9:9ec71ba8 r8:00000000 r7:00000000 r6:9f6b0400 r5:9f56f800 [ 2991.878548] r4:8076278c [ 2991.881110] [<80485988>] (rtnl_newlink) from [<80484048>] (rtnetlink_rcv_msg+0x18c/0x22c) [ 2991.889315] r10:9f7d4e40 r9:00000000 r8:00000000 r7:00000000 r6:9f7d4e40 r5:9f6b0400 [ 2991.897250] r4:00000000 [ 2991.899814] [<80483ebc>] (rtnetlink_rcv_msg) from [<80497c74>] (netlink_rcv_skb+0xb0/0xcc) [ 2991.908104] r8:00000000 r7:9f7d4e40 r6:9f7d4e40 r5:80483ebc r4:9f6b0400 [ 2991.914928] [<80497bc4>] (netlink_rcv_skb) from [<80483eb4>] (rtnetlink_rcv+0x34/0x3c) [ 2991.922874] r6:9f5ea000 r5:00000028 r4:9f7d4e40 r3:80483e80 [ 2991.928622] [<80483e80>] (rtnetlink_rcv) from [<80497604>] (netlink_unicast+0x180/0x200) [ 2991.936742] r4:9f4edc00 r3:80483e80 [ 2991.940362] [<80497484>] (netlink_unicast) from [<80497a88>] (netlink_sendmsg+0x33c/0x350) [ 2991.948648] r8:00000000 r7:00000028 r6:00000000 r5:9f5ea000 r4:9ec71f4c [ 2991.955481] [<8049774c>] (netlink_sendmsg) from [<80457ff0>] (sock_sendmsg+0x24/0x34) [ 2991.963342] r10:00000000 r9:9ec71e28 r8:00000000 r7:9f1e2140 r6:00000000 r5:00000000 [ 2991.971276] r4:9ec71f4c [ 2991.973849] [<80457fcc>] (sock_sendmsg) from [<80458af0>] (___sys_sendmsg+0x1fc/0x204) [ 2991.981809] [<804588f4>] (___sys_sendmsg) from [<804598d0>] (__sys_sendmsg+0x4c/0x7c) [ 2991.989640] r10:00000000 r9:9ec70000 r8:80010824 r7:00000128 r6:7ee946c4 r5:00000000 [ 2991.997572] r4:9f1e2140 [ 2992.000128] [<80459884>] (__sys_sendmsg) from [<80459918>] (SyS_sendmsg+0x18/0x1c) [ 2992.007725] r6:00000000 r5:7ee9c7b8 r4:7ee946e0 [ 2992.012430] [<80459900>] (SyS_sendmsg) from [<80010660>] (ret_fast_syscall+0x0/0x3c) [ 2992.020182] ---[ end trace 5d4bc29f4da04280 ]--- To fix this, return -EOPNOTSUPP in _mv88e6xxx_port_vlan_del instead of -ENOENT if the hardware VLAN doesn't exist or the port is not a member. Signed-off-by: Vivien Didelot Tested-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index cf34681af4f6..d76a4eae1a52 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1555,7 +1555,7 @@ static int _mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, u16 vid) if (vlan.vid != vid || !vlan.valid || vlan.data[port] == GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER) - return -ENOENT; + return -EOPNOTSUPP; vlan.data[port] = GLOBAL_VTU_DATA_MEMBER_TAG_NON_MEMBER; From 66d9cd0f5422bf35e3897b2022858dafd8c6abd2 Mon Sep 17 00:00:00 2001 From: Vivien Didelot Date: Fri, 5 Feb 2016 14:07:14 -0500 Subject: [PATCH 134/489] net: dsa: mv88e6xxx: do not leave reserved VLANs BRIDGE_VLAN_FILTERING automatically adds a newly bridged port to the VLAN with the bridge's default_pvid. The mv88e6xxx driver currently reserves VLANs 4000+ for unbridged ports isolation. When a port joins a bridge, it leaves its reserved VLAN. When a port leaves a bridge, it joins again its reserved VLAN. But if the VLAN filtering is disabled, or if this hardware VLAN is already in use, the bridged port ends up with no default VLAN, and the communication with the CPU is thus broken. To fix this, make a port join its reserved VLAN once on setup, never leave it, and restore its PVID after another one was eventually used. Signed-off-by: Vivien Didelot Tested-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index d76a4eae1a52..512c8c0be1b4 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -1582,6 +1582,7 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, const struct switchdev_obj_port_vlan *vlan) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); + const u16 defpvid = 4000 + ds->index * DSA_MAX_PORTS + port; u16 pvid, vid; int err = 0; @@ -1597,7 +1598,8 @@ int mv88e6xxx_port_vlan_del(struct dsa_switch *ds, int port, goto unlock; if (vid == pvid) { - err = _mv88e6xxx_port_pvid_set(ds, port, 0); + /* restore reserved VLAN ID */ + err = _mv88e6xxx_port_pvid_set(ds, port, defpvid); if (err) goto unlock; } @@ -1889,26 +1891,20 @@ unlock: int mv88e6xxx_port_bridge_join(struct dsa_switch *ds, int port, u32 members) { - struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); - const u16 pvid = 4000 + ds->index * DSA_MAX_PORTS + port; - int err; - - /* The port joined a bridge, so leave its reserved VLAN */ - mutex_lock(&ps->smi_mutex); - err = _mv88e6xxx_port_vlan_del(ds, port, pvid); - if (!err) - err = _mv88e6xxx_port_pvid_set(ds, port, 0); - mutex_unlock(&ps->smi_mutex); - return err; + return 0; } int mv88e6xxx_port_bridge_leave(struct dsa_switch *ds, int port, u32 members) +{ + return 0; +} + +static int mv88e6xxx_setup_port_default_vlan(struct dsa_switch *ds, int port) { struct mv88e6xxx_priv_state *ps = ds_to_priv(ds); const u16 pvid = 4000 + ds->index * DSA_MAX_PORTS + port; int err; - /* The port left the bridge, so join its reserved VLAN */ mutex_lock(&ps->smi_mutex); err = _mv88e6xxx_port_vlan_add(ds, port, pvid, true); if (!err) @@ -2192,8 +2188,7 @@ int mv88e6xxx_setup_ports(struct dsa_switch *ds) if (dsa_is_cpu_port(ds, i) || dsa_is_dsa_port(ds, i)) continue; - /* setup the unbridged state */ - ret = mv88e6xxx_port_bridge_leave(ds, i, 0); + ret = mv88e6xxx_setup_port_default_vlan(ds, i); if (ret < 0) return ret; } From db92ea5d4df00271b57d79c2d03dae5a5d60fcc1 Mon Sep 17 00:00:00 2001 From: Michael McConville Date: Fri, 5 Feb 2016 20:46:25 -0500 Subject: [PATCH 135/489] dscc4: Undefined signed int shift My analysis in the below mail applies, although the second part is unnecessary because i isn't used in arithmetic operations here: https://marc.info/?l=openbsd-tech&m=145377854103866&w=2 Thanks for your time. Signed-off-by: Michael McConville Acked-by: Francois Romieu Signed-off-by: David S. Miller --- drivers/net/wan/dscc4.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index 7a72407208b1..629225980463 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -1626,7 +1626,7 @@ try: if (state & Xpr) { void __iomem *scc_addr; unsigned long ring; - int i; + unsigned int i; /* * - the busy condition happens (sometimes); From 7864d92621b6897595fa698b27240828592ebd71 Mon Sep 17 00:00:00 2001 From: Sebastian Hesselbarth Date: Mon, 1 Feb 2016 23:48:23 +0100 Subject: [PATCH 136/489] pinctrl: mvebu: fix num_settings in mpp group assignment When assigning mpp settings from static mpp modes to mpp groups, we do not want any groups that have no supported setting for a specific Kirkwood variant. However, when there is at least a single supported setting, we need to assign the number of all settings in this mode to grp->num_settings as we are reusing the static modes table. Fixes: 0581b16b1840 ("pinctrl: mvebu: complain about missing group after checking variant") Reported-by: Aaro Koskinen Tested-by: Aaro Koskinen Cc: Gregory Clement Cc: Andrew Lunn Cc: linux-arm-kernel@lists.infradead.org Signed-off-by: Sebastian Hesselbarth Signed-off-by: Linus Walleij --- drivers/pinctrl/mvebu/pinctrl-mvebu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/pinctrl/mvebu/pinctrl-mvebu.c b/drivers/pinctrl/mvebu/pinctrl-mvebu.c index e4d473811bb3..3ef798fac81b 100644 --- a/drivers/pinctrl/mvebu/pinctrl-mvebu.c +++ b/drivers/pinctrl/mvebu/pinctrl-mvebu.c @@ -666,16 +666,19 @@ int mvebu_pinctrl_probe(struct platform_device *pdev) struct mvebu_mpp_ctrl_setting *set = &mode->settings[0]; struct mvebu_pinctrl_group *grp; unsigned num_settings; + unsigned supp_settings; - for (num_settings = 0; ; set++) { + for (num_settings = 0, supp_settings = 0; ; set++) { if (!set->name) break; + num_settings++; + /* skip unsupported settings for this variant */ if (pctl->variant && !(pctl->variant & set->variant)) continue; - num_settings++; + supp_settings++; /* find gpio/gpo/gpi settings */ if (strcmp(set->name, "gpio") == 0) @@ -688,7 +691,7 @@ int mvebu_pinctrl_probe(struct platform_device *pdev) } /* skip modes with no settings for this variant */ - if (!num_settings) + if (!supp_settings) continue; grp = mvebu_pinctrl_find_group_by_pid(pctl, mode->pid); From 5e56276e7555b34550d51459a801ff75eca8b907 Mon Sep 17 00:00:00 2001 From: Luca Coelho Date: Tue, 2 Feb 2016 15:11:15 +0200 Subject: [PATCH 137/489] iwlwifi: mvm: don't allow sched scans without matches to be started The firmware can perform a scheduled scan with not matchsets passed, but it can't send notification that results were found. Since the userspace then cannot know when we got new results and the firmware wouldn't trigger a wake in case we are sleeping, it's better not to allow scans without matchsets. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=110831 Cc: [3.17+] Signed-off-by: Luca Coelho Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 9a15642f80dd..ea1e177c2ea1 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -1298,6 +1298,10 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm, return -EBUSY; } + /* we don't support "match all" in the firmware */ + if (!req->n_match_sets) + return -EOPNOTSUPP; + ret = iwl_mvm_check_running_scans(mvm, type); if (ret) return ret; From 126df08c52375817c237f38c3bcd01d78a60c090 Mon Sep 17 00:00:00 2001 From: Denis Kirjanov Date: Mon, 14 Dec 2015 23:18:06 +0300 Subject: [PATCH 138/489] powerpc/pseries: Don't trace hcalls on offline CPUs If a cpu is hotplugged while the hcall trace points are active, it's possible to hit a warning from RCU due to the trace points calling into RCU from an offline cpu, eg: RCU used illegally from offline CPU! rcu_scheduler_active = 1, debug_locks = 1 Make the hypervisor tracepoints conditional by using TRACE_EVENT_FN_COND. Acked-by: Steven Rostedt Signed-off-by: Denis Kirjanov Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/trace.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/trace.h b/arch/powerpc/include/asm/trace.h index 8e86b48d0369..32e36b16773f 100644 --- a/arch/powerpc/include/asm/trace.h +++ b/arch/powerpc/include/asm/trace.h @@ -57,12 +57,14 @@ DEFINE_EVENT(ppc64_interrupt_class, timer_interrupt_exit, extern void hcall_tracepoint_regfunc(void); extern void hcall_tracepoint_unregfunc(void); -TRACE_EVENT_FN(hcall_entry, +TRACE_EVENT_FN_COND(hcall_entry, TP_PROTO(unsigned long opcode, unsigned long *args), TP_ARGS(opcode, args), + TP_CONDITION(cpu_online(raw_smp_processor_id())), + TP_STRUCT__entry( __field(unsigned long, opcode) ), @@ -76,13 +78,15 @@ TRACE_EVENT_FN(hcall_entry, hcall_tracepoint_regfunc, hcall_tracepoint_unregfunc ); -TRACE_EVENT_FN(hcall_exit, +TRACE_EVENT_FN_COND(hcall_exit, TP_PROTO(unsigned long opcode, unsigned long retval, unsigned long *retbuf), TP_ARGS(opcode, retval, retbuf), + TP_CONDITION(cpu_online(raw_smp_processor_id())), + TP_STRUCT__entry( __field(unsigned long, opcode) __field(unsigned long, retval) From 05ba75f848647135f063199dc0e9f40fee769724 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 9 Feb 2016 15:50:21 +1100 Subject: [PATCH 139/489] powerpc/eeh: Fix stale cached primary bus When PE is created, its primary bus is cached to pe->bus. At later point, the cached primary bus is returned from eeh_pe_bus_get(). However, we could get stale cached primary bus and run into kernel crash in one case: full hotplug as part of fenced PHB error recovery releases all PCI busses under the PHB at unplugging time and recreate them at plugging time. pe->bus is still dereferencing the PCI bus that was released. This adds another PE flag (EEH_PE_PRI_BUS) to represent the validity of pe->bus. pe->bus is updated when its first child EEH device is online and the flag is set. Before unplugging in full hotplug for error recovery, the flag is cleared. Fixes: 8cdb2833 ("powerpc/eeh: Trace PCI bus from PE") Cc: stable@vger.kernel.org #v3.11+ Reported-by: Andrew Donnellan Reported-by: Pradipta Ghosh Signed-off-by: Gavin Shan Tested-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/eeh.h | 1 + arch/powerpc/kernel/eeh_driver.c | 3 +++ arch/powerpc/kernel/eeh_pe.c | 2 +- arch/powerpc/platforms/powernv/eeh-powernv.c | 5 ++++- 4 files changed, 9 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h index c5eb86f3d452..867c39b45df6 100644 --- a/arch/powerpc/include/asm/eeh.h +++ b/arch/powerpc/include/asm/eeh.h @@ -81,6 +81,7 @@ struct pci_dn; #define EEH_PE_KEEP (1 << 8) /* Keep PE on hotplug */ #define EEH_PE_CFG_RESTRICTED (1 << 9) /* Block config on error */ #define EEH_PE_REMOVED (1 << 10) /* Removed permanently */ +#define EEH_PE_PRI_BUS (1 << 11) /* Cached primary bus */ struct eeh_pe { int type; /* PE type: PHB/Bus/Device */ diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index 8d14feb40f12..f69ecaa7ce33 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -564,6 +564,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus) */ eeh_pe_state_mark(pe, EEH_PE_KEEP); if (bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); pci_lock_rescan_remove(); pcibios_remove_pci_devices(bus); pci_unlock_rescan_remove(); @@ -803,6 +804,7 @@ perm_error: * the their PCI config any more. */ if (frozen_bus) { + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); eeh_pe_dev_mode_mark(pe, EEH_DEV_REMOVED); pci_lock_rescan_remove(); @@ -886,6 +888,7 @@ static void eeh_handle_special_event(void) continue; /* Notify all devices to be down */ + eeh_pe_state_clear(pe, EEH_PE_PRI_BUS); bus = eeh_pe_bus_get(phb_pe); eeh_pe_dev_traverse(pe, eeh_report_failure, NULL); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index ca9e5371930e..98f81800e00c 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -928,7 +928,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) bus = pe->phb->bus; } else if (pe->type & EEH_PE_BUS || pe->type & EEH_PE_DEVICE) { - if (pe->bus) { + if (pe->state & EEH_PE_PRI_BUS) { bus = pe->bus; goto out; } diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c index 5f152b95ca0c..87f47e55aab6 100644 --- a/arch/powerpc/platforms/powernv/eeh-powernv.c +++ b/arch/powerpc/platforms/powernv/eeh-powernv.c @@ -444,9 +444,12 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data) * PCI devices of the PE are expected to be removed prior * to PE reset. */ - if (!edev->pe->bus) + if (!(edev->pe->state & EEH_PE_PRI_BUS)) { edev->pe->bus = pci_find_bus(hose->global_number, pdn->busno); + if (edev->pe->bus) + edev->pe->state |= EEH_PE_PRI_BUS; + } /* * Enable EEH explicitly so that we will do EEH check From 1bc74f1ccd457832dc515fc1febe6655985fdcd2 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Tue, 9 Feb 2016 15:50:22 +1100 Subject: [PATCH 140/489] powerpc/powernv: Fix stale PE primary bus When PCI bus is unplugged during full hotplug for EEH recovery, the platform PE instance (struct pnv_ioda_pe) isn't released and it dereferences the stale PCI bus that has been released. It leads to kernel crash when referring to the stale PCI bus. This fixes the issue by correcting the PE's primary bus when it's oneline at plugging time, in pnv_pci_dma_bus_setup() which is to be called by pcibios_fixup_bus(). Cc: stable@vger.kernel.org # v4.1+ Reported-by: Andrew Donnellan Reported-by: Pradipta Ghosh Signed-off-by: Gavin Shan Tested-by: Andrew Donnellan Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/pci-ioda.c | 1 + arch/powerpc/platforms/powernv/pci.c | 20 ++++++++++++++++++++ arch/powerpc/platforms/powernv/pci.h | 1 + 3 files changed, 22 insertions(+) diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 573ae1994097..f90dc04395bf 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3180,6 +3180,7 @@ static void pnv_pci_ioda_shutdown(struct pci_controller *hose) static const struct pci_controller_ops pnv_pci_ioda_controller_ops = { .dma_dev_setup = pnv_pci_dma_dev_setup, + .dma_bus_setup = pnv_pci_dma_bus_setup, #ifdef CONFIG_PCI_MSI .setup_msi_irqs = pnv_setup_msi_irqs, .teardown_msi_irqs = pnv_teardown_msi_irqs, diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index 2f55c86df703..d25ff2292ae2 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -760,6 +760,26 @@ void pnv_pci_dma_dev_setup(struct pci_dev *pdev) phb->dma_dev_setup(phb, pdev); } +void pnv_pci_dma_bus_setup(struct pci_bus *bus) +{ + struct pci_controller *hose = bus->sysdata; + struct pnv_phb *phb = hose->private_data; + struct pnv_ioda_pe *pe; + + list_for_each_entry(pe, &phb->ioda.pe_list, list) { + if (!(pe->flags & (PNV_IODA_PE_BUS | PNV_IODA_PE_BUS_ALL))) + continue; + + if (!pe->pbus) + continue; + + if (bus->number == ((pe->rid >> 8) & 0xFF)) { + pe->pbus = bus; + break; + } + } +} + void pnv_pci_shutdown(void) { struct pci_controller *hose; diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h index 7f56313e8d72..00691a9b99af 100644 --- a/arch/powerpc/platforms/powernv/pci.h +++ b/arch/powerpc/platforms/powernv/pci.h @@ -242,6 +242,7 @@ extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev); extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option); extern void pnv_pci_dma_dev_setup(struct pci_dev *pdev); +extern void pnv_pci_dma_bus_setup(struct pci_bus *bus); extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type); extern void pnv_teardown_msi_irqs(struct pci_dev *pdev); From c777e2a8b65420b31dac28a453e35be984f5808b Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Tue, 9 Feb 2016 06:50:31 +0530 Subject: [PATCH 141/489] powerpc/mm: Fix Multi hit ERAT cause by recent THP update With ppc64 we use the deposited pgtable_t to store the hash pte slot information. We should not withdraw the deposited pgtable_t without marking the pmd none. This ensure that low level hash fault handling will skip this huge pte and we will handle them at upper levels. Recent change to pmd splitting changed the above in order to handle the race between pmd split and exit_mmap. The race is explained below. Consider following race: CPU0 CPU1 shrink_page_list() add_to_swap() split_huge_page_to_list() __split_huge_pmd_locked() pmdp_huge_clear_flush_notify() // pmd_none() == true exit_mmap() unmap_vmas() zap_pmd_range() // no action on pmd since pmd_none() == true pmd_populate() As result the THP will not be freed. The leak is detected by check_mm(): BUG: Bad rss-counter state mm:ffff880058d2e580 idx:1 val:512 The above required us to not mark pmd none during a pmd split. The fix for ppc is to clear the huge pte of _PAGE_USER, so that low level fault handling code skip this pte. At higher level we do take ptl lock. That should serialze us against the pmd split. Once the lock is acquired we do check the pmd again using pmd_same. That should always return false for us and hence we should retry the access. We do the pmd_same check in all case after taking plt with THP (do_huge_pmd_wp_page, do_huge_pmd_numa_page and huge_pmd_set_accessed) Also make sure we wait for irq disable section in other cpus to finish before flipping a huge pte entry with a regular pmd entry. Code paths like find_linux_pte_or_hugepte depend on irq disable to get a stable pte_t pointer. A parallel thp split need to make sure we don't convert a pmd pte to a regular pmd entry without waiting for the irq disable section to finish. Fixes: eef1b3ba053a ("thp: implement split_huge_pmd()") Acked-by: Kirill A. Shutemov Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/include/asm/book3s/64/pgtable.h | 4 +++ arch/powerpc/mm/pgtable_64.c | 32 ++++++++++++++++++++ include/asm-generic/pgtable.h | 8 +++++ mm/huge_memory.c | 1 + 4 files changed, 45 insertions(+) diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 8d1c41d28318..ac07a30a7934 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -281,6 +281,10 @@ extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp); extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); +#define __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE +extern void pmdp_huge_split_prepare(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + #define pmd_move_must_withdraw pmd_move_must_withdraw struct spinlock; static inline int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl, diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c index 3124a20d0fab..cdf2123d46db 100644 --- a/arch/powerpc/mm/pgtable_64.c +++ b/arch/powerpc/mm/pgtable_64.c @@ -646,6 +646,28 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp) return pgtable; } +void pmdp_huge_split_prepare(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(REGION_ID(address) != USER_REGION_ID); + + /* + * We can't mark the pmd none here, because that will cause a race + * against exit_mmap. We need to continue mark pmd TRANS HUGE, while + * we spilt, but at the same time we wan't rest of the ppc64 code + * not to insert hash pte on this, because we will be modifying + * the deposited pgtable in the caller of this function. Hence + * clear the _PAGE_USER so that we move the fault handling to + * higher level function and that will serialize against ptl. + * We need to flush existing hash pte entries here even though, + * the translation is still valid, because we will withdraw + * pgtable_t after this. + */ + pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_USER, 0); +} + + /* * set a new huge pmd. We should not be called for updating * an existing pmd entry. That should go via pmd_hugepage_update. @@ -663,10 +685,20 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr, return set_pte_at(mm, addr, pmdp_ptep(pmdp), pmd_pte(pmd)); } +/* + * We use this to invalidate a pmdp entry before switching from a + * hugepte to regular pmd entry. + */ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_hugepage_update(vma->vm_mm, address, pmdp, _PAGE_PRESENT, 0); + + /* + * This ensures that generic code that rely on IRQ disabling + * to prevent a parallel THP split work as expected. + */ + kick_all_cpus_sync(); } /* diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index 0b3c0d39ef75..c370b261c720 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -239,6 +239,14 @@ extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp); #endif +#ifndef __HAVE_ARCH_PMDP_HUGE_SPLIT_PREPARE +static inline void pmdp_huge_split_prepare(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + +} +#endif + #ifndef __HAVE_ARCH_PTE_SAME static inline int pte_same(pte_t pte_a, pte_t pte_b) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b1cf73bc3b12..de3f43cde129 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2856,6 +2856,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, young = pmd_young(*pmd); dirty = pmd_dirty(*pmd); + pmdp_huge_split_prepare(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); From a6bd005fe92dc1cc808c4c6aa43e3b2a8272bbfa Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Sun, 31 Jan 2016 15:02:30 +0200 Subject: [PATCH 142/489] iwlwifi: pcie: fix RF-Kill vs. firmware load race When we load the firmware, we hold trans_pcie->mutex to avoid nested flows. We also rely on the ISR to wake up the thread when the DMA has finished copying a chunk. During this flow, we enable the RF-Kill interrupt. The problem is that the RF-Kill interrupt handler can take the mutex and bring the device down. This means that if we load the firmware while the RF-Kill switch is enabled (which will happen when we load the INIT firmware to read the device's capabilities and register to mac80211), we may get an RF-Kill interrupt immediately and the ISR will be waiting for the mutex held by the thread that is currently loading the firmware. At this stage, the ISR won't be able to service the DMA's interrupt needed to wake up the thread that load the firmware. We are in a deadlock situation which ends when the thread that loads the firmware fails on timeout and releases the mutex. To fix this, take the mutex later in the flow, disable the interrupts and synchronize_irq() to give a chance to the RF-Kill interrupt to run and complete. After that, mask all the interrupts besides the DMA interrupt and proceed with firmware load. Make sure to check that there was no RF-Kill interrupt when the interrupts were disabled. This fixes https://bugzilla.kernel.org/show_bug.cgi?id=111361 Signed-off-by: Emmanuel Grumbach --- .../wireless/intel/iwlwifi/pcie/internal.h | 9 + drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 8 +- .../net/wireless/intel/iwlwifi/pcie/trans.c | 188 ++++++++++-------- 3 files changed, 123 insertions(+), 82 deletions(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h index cc3888e2700d..73c95594eabe 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h +++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h @@ -490,6 +490,15 @@ static inline void iwl_enable_interrupts(struct iwl_trans *trans) iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask); } +static inline void iwl_enable_fw_load_int(struct iwl_trans *trans) +{ + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + + IWL_DEBUG_ISR(trans, "Enabling FW load interrupt\n"); + trans_pcie->inta_mask = CSR_INT_BIT_FH_TX; + iwl_write32(trans, CSR_INT_MASK, trans_pcie->inta_mask); +} + static inline void iwl_enable_rfkill_int(struct iwl_trans *trans) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c index ccafbd8cf4b3..152cf9ad9566 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c @@ -1438,9 +1438,11 @@ irqreturn_t iwl_pcie_irq_handler(int irq, void *dev_id) inta & ~trans_pcie->inta_mask); } - /* Re-enable all interrupts */ - /* only Re-enable if disabled by irq */ - if (test_bit(STATUS_INT_ENABLED, &trans->status)) + /* we are loading the firmware, enable FH_TX interrupt only */ + if (handled & CSR_INT_BIT_FH_TX) + iwl_enable_fw_load_int(trans); + /* only Re-enable all interrupt if disabled by irq */ + else if (test_bit(STATUS_INT_ENABLED, &trans->status)) iwl_enable_interrupts(trans); /* Re-enable RF_KILL if it occurred */ else if (handled & CSR_INT_BIT_RF_KILL) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index d60a467a983c..55030729c7d9 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1021,82 +1021,6 @@ static int iwl_pcie_load_given_ucode_8000(struct iwl_trans *trans, &first_ucode_section); } -static int iwl_trans_pcie_start_fw(struct iwl_trans *trans, - const struct fw_img *fw, bool run_in_rfkill) -{ - struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); - bool hw_rfkill; - int ret; - - mutex_lock(&trans_pcie->mutex); - - /* Someone called stop_device, don't try to start_fw */ - if (trans_pcie->is_down) { - IWL_WARN(trans, - "Can't start_fw since the HW hasn't been started\n"); - ret = EIO; - goto out; - } - - /* This may fail if AMT took ownership of the device */ - if (iwl_pcie_prepare_card_hw(trans)) { - IWL_WARN(trans, "Exit HW not ready\n"); - ret = -EIO; - goto out; - } - - iwl_enable_rfkill_int(trans); - - /* If platform's RF_KILL switch is NOT set to KILL */ - hw_rfkill = iwl_is_rfkill_set(trans); - if (hw_rfkill) - set_bit(STATUS_RFKILL, &trans->status); - else - clear_bit(STATUS_RFKILL, &trans->status); - iwl_trans_pcie_rf_kill(trans, hw_rfkill); - if (hw_rfkill && !run_in_rfkill) { - ret = -ERFKILL; - goto out; - } - - iwl_write32(trans, CSR_INT, 0xFFFFFFFF); - - ret = iwl_pcie_nic_init(trans); - if (ret) { - IWL_ERR(trans, "Unable to init nic\n"); - goto out; - } - - /* make sure rfkill handshake bits are cleared */ - iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL); - iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, - CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED); - - /* clear (again), then enable host interrupts */ - iwl_write32(trans, CSR_INT, 0xFFFFFFFF); - iwl_enable_interrupts(trans); - - /* really make sure rfkill handshake bits are cleared */ - iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL); - iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL); - - /* Load the given image to the HW */ - if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) - ret = iwl_pcie_load_given_ucode_8000(trans, fw); - else - ret = iwl_pcie_load_given_ucode(trans, fw); - -out: - mutex_unlock(&trans_pcie->mutex); - return ret; -} - -static void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr) -{ - iwl_pcie_reset_ict(trans); - iwl_pcie_tx_start(trans, scd_addr); -} - static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); @@ -1127,7 +1051,8 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power) * already dead. */ if (test_and_clear_bit(STATUS_DEVICE_ENABLED, &trans->status)) { - IWL_DEBUG_INFO(trans, "DEVICE_ENABLED bit was set and is now cleared\n"); + IWL_DEBUG_INFO(trans, + "DEVICE_ENABLED bit was set and is now cleared\n"); iwl_pcie_tx_stop(trans); iwl_pcie_rx_stop(trans); @@ -1161,7 +1086,6 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power) iwl_disable_interrupts(trans); spin_unlock(&trans_pcie->irq_lock); - /* clear all status bits */ clear_bit(STATUS_SYNC_HCMD_ACTIVE, &trans->status); clear_bit(STATUS_INT_ENABLED, &trans->status); @@ -1194,10 +1118,116 @@ static void _iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power) if (hw_rfkill != was_hw_rfkill) iwl_trans_pcie_rf_kill(trans, hw_rfkill); - /* re-take ownership to prevent other users from stealing the deivce */ + /* re-take ownership to prevent other users from stealing the device */ iwl_pcie_prepare_card_hw(trans); } +static int iwl_trans_pcie_start_fw(struct iwl_trans *trans, + const struct fw_img *fw, bool run_in_rfkill) +{ + struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); + bool hw_rfkill; + int ret; + + /* This may fail if AMT took ownership of the device */ + if (iwl_pcie_prepare_card_hw(trans)) { + IWL_WARN(trans, "Exit HW not ready\n"); + ret = -EIO; + goto out; + } + + iwl_enable_rfkill_int(trans); + + iwl_write32(trans, CSR_INT, 0xFFFFFFFF); + + /* + * We enabled the RF-Kill interrupt and the handler may very + * well be running. Disable the interrupts to make sure no other + * interrupt can be fired. + */ + iwl_disable_interrupts(trans); + + /* Make sure it finished running */ + synchronize_irq(trans_pcie->pci_dev->irq); + + mutex_lock(&trans_pcie->mutex); + + /* If platform's RF_KILL switch is NOT set to KILL */ + hw_rfkill = iwl_is_rfkill_set(trans); + if (hw_rfkill) + set_bit(STATUS_RFKILL, &trans->status); + else + clear_bit(STATUS_RFKILL, &trans->status); + iwl_trans_pcie_rf_kill(trans, hw_rfkill); + if (hw_rfkill && !run_in_rfkill) { + ret = -ERFKILL; + goto out; + } + + /* Someone called stop_device, don't try to start_fw */ + if (trans_pcie->is_down) { + IWL_WARN(trans, + "Can't start_fw since the HW hasn't been started\n"); + ret = EIO; + goto out; + } + + /* make sure rfkill handshake bits are cleared */ + iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL); + iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, + CSR_UCODE_DRV_GP1_BIT_CMD_BLOCKED); + + /* clear (again), then enable host interrupts */ + iwl_write32(trans, CSR_INT, 0xFFFFFFFF); + + ret = iwl_pcie_nic_init(trans); + if (ret) { + IWL_ERR(trans, "Unable to init nic\n"); + goto out; + } + + /* + * Now, we load the firmware and don't want to be interrupted, even + * by the RF-Kill interrupt (hence mask all the interrupt besides the + * FH_TX interrupt which is needed to load the firmware). If the + * RF-Kill switch is toggled, we will find out after having loaded + * the firmware and return the proper value to the caller. + */ + iwl_enable_fw_load_int(trans); + + /* really make sure rfkill handshake bits are cleared */ + iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL); + iwl_write32(trans, CSR_UCODE_DRV_GP1_CLR, CSR_UCODE_SW_BIT_RFKILL); + + /* Load the given image to the HW */ + if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) + ret = iwl_pcie_load_given_ucode_8000(trans, fw); + else + ret = iwl_pcie_load_given_ucode(trans, fw); + iwl_enable_interrupts(trans); + + /* re-check RF-Kill state since we may have missed the interrupt */ + hw_rfkill = iwl_is_rfkill_set(trans); + if (hw_rfkill) + set_bit(STATUS_RFKILL, &trans->status); + else + clear_bit(STATUS_RFKILL, &trans->status); + + iwl_trans_pcie_rf_kill(trans, hw_rfkill); + if (hw_rfkill && !run_in_rfkill) + ret = -ERFKILL; + +out: + mutex_unlock(&trans_pcie->mutex); + return ret; +} + +static void iwl_trans_pcie_fw_alive(struct iwl_trans *trans, u32 scd_addr) +{ + iwl_pcie_reset_ict(trans); + iwl_pcie_tx_start(trans, scd_addr); +} + static void iwl_trans_pcie_stop_device(struct iwl_trans *trans, bool low_power) { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); From 20aa99bbddae74bded68338f9ba200ccae02858b Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Thu, 11 Feb 2016 08:35:15 +0200 Subject: [PATCH 143/489] iwlwifi: pcie: fix erroneous return value The iwl_trans_pcie_start_fw() function may return the positive value EIO instead of -EIO in case of error. Signed-off-by: Anton Protopopov Signed-off-by: Emmanuel Grumbach --- drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 55030729c7d9..5a854c609477 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -1168,7 +1168,7 @@ static int iwl_trans_pcie_start_fw(struct iwl_trans *trans, if (trans_pcie->is_down) { IWL_WARN(trans, "Can't start_fw since the HW hasn't been started\n"); - ret = EIO; + ret = -EIO; goto out; } From 814a3c0c2a8dfad97089f6bdc71b374f6076490e Mon Sep 17 00:00:00 2001 From: Tony Lindgren Date: Wed, 10 Feb 2016 15:02:44 -0800 Subject: [PATCH 144/489] mmc: omap_hsmmc: Fix PM regression with deferred probe for pm_runtime_reinit Commit 5de85b9d57ab ("PM / runtime: Re-init runtime PM states at probe error and driver unbind") introduced pm_runtime_reinit() that is used to reinitialize PM runtime after -EPROBE_DEFER. This allows shutting down the device after a failed probe. However, for drivers using pm_runtime_use_autosuspend() this can cause a state where suspend callback is never called after -EPROBE_DEFER. On the following device driver probe, hardware state is different from the PM runtime state causing omap_device to produce the following error: omap_device_enable() called from invalid state 1 And with omap_device and omap hardware being picky for PM, this will block any deeper idle states in hardware. The solution is to fix the drivers to follow the PM runtime documentation: 1. For sections of code that needs the device disabled, use pm_runtime_put_sync_suspend() if pm_runtime_set_autosuspend() has been set. 2. For driver exit code, use pm_runtime_dont_use_autosuspend() before pm_runtime_put_sync() if pm_runtime_use_autosuspend() has been set. Fixes: 5de85b9d57ab ("PM / runtime: Re-init runtime PM states at probe error and driver unbind") Cc: linux-mmc@vger.kernel.org Cc: Alan Stern Cc: Kevin Hilman Cc: Nishanth Menon Cc: Rafael J. Wysocki Cc: Ulf Hansson Cc: Tero Kristo Signed-off-by: Tony Lindgren Signed-off-by: Ulf Hansson --- drivers/mmc/host/omap_hsmmc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c index b6639ea0bf18..f6e4d9718035 100644 --- a/drivers/mmc/host/omap_hsmmc.c +++ b/drivers/mmc/host/omap_hsmmc.c @@ -2232,6 +2232,7 @@ err_irq: dma_release_channel(host->tx_chan); if (host->rx_chan) dma_release_channel(host->rx_chan); + pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); if (host->dbclk) @@ -2253,6 +2254,7 @@ static int omap_hsmmc_remove(struct platform_device *pdev) dma_release_channel(host->tx_chan); dma_release_channel(host->rx_chan); + pm_runtime_dont_use_autosuspend(host->dev); pm_runtime_put_sync(host->dev); pm_runtime_disable(host->dev); device_init_wakeup(&pdev->dev, false); From 85c0a87cd117e83361932b2b160c9af178fdb21a Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Mon, 18 Jan 2016 11:54:43 -0500 Subject: [PATCH 145/489] xen: fix potential integer overflow in queue_reply When len is greater than UINT_MAX - sizeof(*rb), in next allocation, it can overflow integer range and allocates small size of heap. After that, memcpy will overflow the allocated heap. Therefore, it needs to check the size of given length. Signed-off-by: Insu Yun Signed-off-by: David Vrabel --- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 9433e46518c8..912b64edb42b 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -188,6 +188,8 @@ static int queue_reply(struct list_head *queue, const void *data, size_t len) if (len == 0) return 0; + if (len > XENSTORE_PAYLOAD_MAX) + return -EINVAL; rb = kmalloc(sizeof(*rb) + len, GFP_KERNEL); if (rb == NULL) From 8d47065f7d1980dde52abb874b301054f3013602 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:23 -0500 Subject: [PATCH 146/489] xen/pciback: Check PF instead of VF for PCI_COMMAND_MEMORY Commit 408fb0e5aa7fda0059db282ff58c3b2a4278baa0 (xen/pciback: Don't allow MSI-X ops if PCI_COMMAND_MEMORY is not set) prevented enabling MSI-X on passed-through virtual functions, because it checked the VF for PCI_COMMAND_MEMORY but this is not a valid bit for VFs. Instead, check the physical function for PCI_COMMAND_MEMORY. Signed-off-by: Konrad Rzeszutek Wilk Cc: Reviewed-by: Jan Beulich Signed-off-by: David Vrabel --- drivers/xen/xen-pciback/pciback_ops.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 73dafdc494aa..1078e8d631c9 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -227,8 +227,9 @@ int xen_pcibk_enable_msix(struct xen_pcibk_device *pdev, /* * PCI_COMMAND_MEMORY must be enabled, otherwise we may not be able * to access the BARs where the MSI-X entries reside. + * But VF devices are unique in which the PF needs to be checked. */ - pci_read_config_word(dev, PCI_COMMAND, &cmd); + pci_read_config_word(pci_physfn(dev), PCI_COMMAND, &cmd); if (dev->msi_enabled || !(cmd & PCI_COMMAND_MEMORY)) return -ENXIO; From d159457b84395927b5a52adb72f748dd089ad5e5 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:24 -0500 Subject: [PATCH 147/489] xen/pciback: Save the number of MSI-X entries to be copied later. Commit 8135cf8b092723dbfcc611fe6fdcb3a36c9951c5 (xen/pciback: Save xen_pci_op commands before processing it) broke enabling MSI-X because it would never copy the resulting vectors into the response. The number of vectors requested was being overwritten by the return value (typically zero for success). Save the number of vectors before processing the op, so the correct number of vectors are copied afterwards. Signed-off-by: Konrad Rzeszutek Wilk Cc: Reviewed-by: Jan Beulich Signed-off-by: David Vrabel --- drivers/xen/xen-pciback/pciback_ops.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/xen/xen-pciback/pciback_ops.c b/drivers/xen/xen-pciback/pciback_ops.c index 1078e8d631c9..fb0221434f81 100644 --- a/drivers/xen/xen-pciback/pciback_ops.c +++ b/drivers/xen/xen-pciback/pciback_ops.c @@ -333,6 +333,9 @@ void xen_pcibk_do_op(struct work_struct *data) struct xen_pcibk_dev_data *dev_data = NULL; struct xen_pci_op *op = &pdev->op; int test_intx = 0; +#ifdef CONFIG_PCI_MSI + unsigned int nr = 0; +#endif *op = pdev->sh_info->op; barrier(); @@ -361,6 +364,7 @@ void xen_pcibk_do_op(struct work_struct *data) op->err = xen_pcibk_disable_msi(pdev, dev, op); break; case XEN_PCI_OP_enable_msix: + nr = op->value; op->err = xen_pcibk_enable_msix(pdev, dev, op); break; case XEN_PCI_OP_disable_msix: @@ -383,7 +387,7 @@ void xen_pcibk_do_op(struct work_struct *data) if (op->cmd == XEN_PCI_OP_enable_msix && op->err == 0) { unsigned int i; - for (i = 0; i < op->value; i++) + for (i = 0; i < nr; i++) pdev->sh_info->op.msix_entries[i].vector = op->msix_entries[i].vector; } From 2cfec6a2f989d5c921ba11a329ff8ea986702b9b Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:25 -0500 Subject: [PATCH 148/489] xen/pcifront: Report the errors better. The messages should be different depending on the type of error. Signed-off-by: Konrad Rzeszutek Wilk Signed-off-by: David Vrabel --- arch/x86/include/asm/xen/pci.h | 4 ++-- arch/x86/pci/xen.c | 5 ++++- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h index 968d57dd54c9..f320ee32d5a1 100644 --- a/arch/x86/include/asm/xen/pci.h +++ b/arch/x86/include/asm/xen/pci.h @@ -57,7 +57,7 @@ static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msi) return xen_pci_frontend->enable_msi(dev, vectors); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) { @@ -69,7 +69,7 @@ static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, { if (xen_pci_frontend && xen_pci_frontend->enable_msix) return xen_pci_frontend->enable_msix(dev, vectors, nvec); - return -ENODEV; + return -ENOSYS; } static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev) { diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index ff31ab464213..beac4dfdade6 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -196,7 +196,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; error: - dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + if (ret == -ENOSYS) + dev_err(&dev->dev, "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + else if (ret) + dev_err(&dev->dev, "Xen PCI frontend error: %d!\n", ret); free: kfree(v); return ret; From c327cd635c5367d9d6b063dd2d8c78484d4e4fb3 Mon Sep 17 00:00:00 2001 From: Joonyoung Shim Date: Wed, 3 Feb 2016 13:42:45 +0100 Subject: [PATCH 149/489] drm/exynos: depend on ARCH_EXYNOS for DRM_EXYNOS Because PLAT_SAMSUNG isn't include exynos SoCs for arm64, but ARCH_EXYNOS can do it. And it also needs to add ARCH_S3C64XX instead of PLAT_SAMSUNG. Signed-off-by: Joonyoung Shim Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/Kconfig | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/Kconfig b/drivers/gpu/drm/exynos/Kconfig index 83efca941388..f17d39279596 100644 --- a/drivers/gpu/drm/exynos/Kconfig +++ b/drivers/gpu/drm/exynos/Kconfig @@ -1,6 +1,6 @@ config DRM_EXYNOS tristate "DRM Support for Samsung SoC EXYNOS Series" - depends on OF && DRM && (PLAT_SAMSUNG || ARCH_MULTIPLATFORM) + depends on OF && DRM && (ARCH_S3C64XX || ARCH_EXYNOS || ARCH_MULTIPLATFORM) select DRM_KMS_HELPER select DRM_KMS_FB_HELPER select FB_CFB_FILLRECT From 977b5067c232020c5e27842aa5bec3e93d336e60 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:46 +0100 Subject: [PATCH 150/489] drm/exynos: ipp: fix incorrect format specifiers in debug messages Drivers should use %p for printing pointers instead of hardcoding them as hexadecimal integers. This patch fixes compilation warnings on 64bit architectures. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_fimc.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_gsc.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_ipp.c | 32 ++++++++++----------- drivers/gpu/drm/exynos/exynos_drm_rotator.c | 2 +- 4 files changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c index c747824f3c98..8a4f4a0211d0 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c @@ -1723,7 +1723,7 @@ static int fimc_probe(struct platform_device *pdev) goto err_put_clk; } - DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv); + DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv); spin_lock_init(&ctx->lock); platform_set_drvdata(pdev, ctx); diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 7aecd23cfa11..5d20da8f957e 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1723,7 +1723,7 @@ static int gsc_probe(struct platform_device *pdev) return ret; } - DRM_DEBUG_KMS("id[%d]ippdrv[0x%x]\n", ctx->id, (int)ippdrv); + DRM_DEBUG_KMS("id[%d]ippdrv[%p]\n", ctx->id, ippdrv); mutex_init(&ctx->lock); platform_set_drvdata(pdev, ctx); diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c index 67d24236e745..95eeb9116f10 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c +++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c @@ -208,7 +208,7 @@ static struct exynos_drm_ippdrv *ipp_find_drv_by_handle(u32 prop_id) * e.g PAUSE state, queue buf, command control. */ list_for_each_entry(ippdrv, &exynos_drm_ippdrv_list, drv_list) { - DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n", count++, (int)ippdrv); + DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n", count++, ippdrv); mutex_lock(&ippdrv->cmd_lock); list_for_each_entry(c_node, &ippdrv->cmd_list, list) { @@ -388,8 +388,8 @@ int exynos_drm_ipp_set_property(struct drm_device *drm_dev, void *data, } property->prop_id = ret; - DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[0x%x]\n", - property->prop_id, property->cmd, (int)ippdrv); + DRM_DEBUG_KMS("created prop_id[%d]cmd[%d]ippdrv[%p]\n", + property->prop_id, property->cmd, ippdrv); /* stored property information and ippdrv in private data */ c_node->property = *property; @@ -518,7 +518,7 @@ static int ipp_put_mem_node(struct drm_device *drm_dev, { int i; - DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node); + DRM_DEBUG_KMS("node[%p]\n", m_node); if (!m_node) { DRM_ERROR("invalid dequeue node.\n"); @@ -562,7 +562,7 @@ static struct drm_exynos_ipp_mem_node m_node->buf_id = qbuf->buf_id; INIT_LIST_HEAD(&m_node->list); - DRM_DEBUG_KMS("m_node[0x%x]ops_id[%d]\n", (int)m_node, qbuf->ops_id); + DRM_DEBUG_KMS("m_node[%p]ops_id[%d]\n", m_node, qbuf->ops_id); DRM_DEBUG_KMS("prop_id[%d]buf_id[%d]\n", qbuf->prop_id, m_node->buf_id); for_each_ipp_planar(i) { @@ -582,8 +582,8 @@ static struct drm_exynos_ipp_mem_node buf_info->handles[i] = qbuf->handle[i]; buf_info->base[i] = *addr; - DRM_DEBUG_KMS("i[%d]base[0x%x]hd[0x%lx]\n", i, - buf_info->base[i], buf_info->handles[i]); + DRM_DEBUG_KMS("i[%d]base[%pad]hd[0x%lx]\n", i, + &buf_info->base[i], buf_info->handles[i]); } } @@ -664,7 +664,7 @@ static void ipp_put_event(struct drm_exynos_ipp_cmd_node *c_node, mutex_lock(&c_node->event_lock); list_for_each_entry_safe(e, te, &c_node->event_list, base.link) { - DRM_DEBUG_KMS("count[%d]e[0x%x]\n", count++, (int)e); + DRM_DEBUG_KMS("count[%d]e[%p]\n", count++, e); /* * qbuf == NULL condition means all event deletion. @@ -755,7 +755,7 @@ static struct drm_exynos_ipp_mem_node /* find memory node from memory list */ list_for_each_entry(m_node, head, list) { - DRM_DEBUG_KMS("count[%d]m_node[0x%x]\n", count++, (int)m_node); + DRM_DEBUG_KMS("count[%d]m_node[%p]\n", count++, m_node); /* compare buffer id */ if (m_node->buf_id == qbuf->buf_id) @@ -772,7 +772,7 @@ static int ipp_set_mem_node(struct exynos_drm_ippdrv *ippdrv, struct exynos_drm_ipp_ops *ops = NULL; int ret = 0; - DRM_DEBUG_KMS("node[0x%x]\n", (int)m_node); + DRM_DEBUG_KMS("node[%p]\n", m_node); if (!m_node) { DRM_ERROR("invalid queue node.\n"); @@ -1237,7 +1237,7 @@ static int ipp_start_property(struct exynos_drm_ippdrv *ippdrv, m_node = list_first_entry(head, struct drm_exynos_ipp_mem_node, list); - DRM_DEBUG_KMS("m_node[0x%x]\n", (int)m_node); + DRM_DEBUG_KMS("m_node[%p]\n", m_node); ret = ipp_set_mem_node(ippdrv, c_node, m_node); if (ret) { @@ -1610,8 +1610,8 @@ static int ipp_subdrv_probe(struct drm_device *drm_dev, struct device *dev) } ippdrv->prop_list.ipp_id = ret; - DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]ipp_id[%d]\n", - count++, (int)ippdrv, ret); + DRM_DEBUG_KMS("count[%d]ippdrv[%p]ipp_id[%d]\n", + count++, ippdrv, ret); /* store parent device for node */ ippdrv->parent_dev = dev; @@ -1668,7 +1668,7 @@ static int ipp_subdrv_open(struct drm_device *drm_dev, struct device *dev, file_priv->ipp_dev = dev; - DRM_DEBUG_KMS("done priv[0x%x]\n", (int)dev); + DRM_DEBUG_KMS("done priv[%p]\n", dev); return 0; } @@ -1685,8 +1685,8 @@ static void ipp_subdrv_close(struct drm_device *drm_dev, struct device *dev, mutex_lock(&ippdrv->cmd_lock); list_for_each_entry_safe(c_node, tc_node, &ippdrv->cmd_list, list) { - DRM_DEBUG_KMS("count[%d]ippdrv[0x%x]\n", - count++, (int)ippdrv); + DRM_DEBUG_KMS("count[%d]ippdrv[%p]\n", + count++, ippdrv); if (c_node->filp == file) { /* diff --git a/drivers/gpu/drm/exynos/exynos_drm_rotator.c b/drivers/gpu/drm/exynos/exynos_drm_rotator.c index bea0f7826d30..ce59f4443394 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_rotator.c +++ b/drivers/gpu/drm/exynos/exynos_drm_rotator.c @@ -754,7 +754,7 @@ static int rotator_probe(struct platform_device *pdev) goto err_ippdrv_register; } - DRM_DEBUG_KMS("ippdrv[0x%x]\n", (int)ippdrv); + DRM_DEBUG_KMS("ippdrv[%p]\n", ippdrv); platform_set_drvdata(pdev, rot); From 0f10c71a10d04e86fd842d621f678ee1fd233695 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:47 +0100 Subject: [PATCH 151/489] drm/exynos: fix types for compilation on 64bit architectures This patch fixes compilation warnings (on 64bit architectures) and bugs related to casting pointers through 32bit integers. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_g2d.c | 5 +++-- drivers/gpu/drm/exynos/exynos_drm_gem.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_vidi.c | 8 +++++--- 3 files changed, 9 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c index c17efdb238a6..8dfe6e113a88 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c +++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c @@ -1166,7 +1166,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data, goto err_free_event; } - cmd = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd; + cmd = (struct drm_exynos_g2d_cmd *)(unsigned long)req->cmd; if (copy_from_user(cmdlist->data + cmdlist->last, (void __user *)cmd, @@ -1184,7 +1184,8 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data, if (req->cmd_buf_nr) { struct drm_exynos_g2d_cmd *cmd_buf; - cmd_buf = (struct drm_exynos_g2d_cmd *)(uint32_t)req->cmd_buf; + cmd_buf = (struct drm_exynos_g2d_cmd *) + (unsigned long)req->cmd_buf; if (copy_from_user(cmdlist->data + cmdlist->last, (void __user *)cmd_buf, diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 32358c5e3db4..47d126ab6e07 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -218,7 +218,7 @@ static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev, return ERR_PTR(ret); } - DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp); + DRM_DEBUG_KMS("created file object = %p\n", obj->filp); return exynos_gem; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c index 62ac4e5fa51d..b605bd7395ec 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c @@ -223,7 +223,7 @@ static void vidi_fake_vblank_handler(struct work_struct *work) } } -static int vidi_show_connection(struct device *dev, +static ssize_t vidi_show_connection(struct device *dev, struct device_attribute *attr, char *buf) { struct vidi_context *ctx = dev_get_drvdata(dev); @@ -238,7 +238,7 @@ static int vidi_show_connection(struct device *dev, return rc; } -static int vidi_store_connection(struct device *dev, +static ssize_t vidi_store_connection(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -294,7 +294,9 @@ int vidi_connection_ioctl(struct drm_device *drm_dev, void *data, } if (vidi->connection) { - struct edid *raw_edid = (struct edid *)(uint32_t)vidi->edid; + struct edid *raw_edid; + + raw_edid = (struct edid *)(unsigned long)vidi->edid; if (!drm_edid_is_valid(raw_edid)) { DRM_DEBUG_KMS("edid data is invalid.\n"); return -EINVAL; From 38b5e5f4d76df1116b0b5a76fb9b7549a44efe6e Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:48 +0100 Subject: [PATCH 152/489] drm/exynos: mic: use devm_clk interface Drivers should use devm_clk* interface instead of of_clk* functions. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_mic.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 4eaef36aec5a..10594c17097a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -445,7 +445,7 @@ int exynos_mic_probe(struct platform_device *pdev) } for (i = 0; i < NUM_CLKS; i++) { - mic->clks[i] = of_clk_get_by_name(dev->of_node, clk_names[i]); + mic->clks[i] = devm_clk_get(dev, clk_names[i]); if (IS_ERR(mic->clks[i])) { DRM_ERROR("mic: Failed to get clock (%s)\n", clk_names[i]); @@ -463,13 +463,9 @@ err: static int exynos_mic_remove(struct platform_device *pdev) { struct exynos_mic *mic = platform_get_drvdata(pdev); - int i; drm_bridge_remove(&mic->bridge); - for (i = NUM_CLKS - 1; i > -1; i--) - clk_put(mic->clks[i]); - return 0; } From 622688f36e9b98ab0c0a01a47c33635519e735cb Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:49 +0100 Subject: [PATCH 153/489] drm/exynos: mic: convert to component framework MIC is SoC component and important part of kms pipeline on Exynos5433, so convert it to use component framework like other KMS/CRTC drivers. MIC driver is already listed on KMS component driver list in Exynos DRM core, so without this conversion, initialization of Exynos DRM core fails on Exynos 5433 SoC. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_mic.c | 56 ++++++++++++++++--------- 1 file changed, 36 insertions(+), 20 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 10594c17097a..899061a35cf6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -373,9 +374,33 @@ already_enabled: void mic_enable(struct drm_bridge *bridge) { } -void mic_destroy(struct drm_bridge *bridge) +static const struct drm_bridge_funcs mic_bridge_funcs = { + .disable = mic_disable, + .post_disable = mic_post_disable, + .pre_enable = mic_pre_enable, + .enable = mic_enable, +}; + +static int exynos_mic_bind(struct device *dev, struct device *master, + void *data) { - struct exynos_mic *mic = bridge->driver_private; + struct exynos_mic *mic = dev_get_drvdata(dev); + int ret; + + mic->bridge.funcs = &mic_bridge_funcs; + mic->bridge.of_node = dev->of_node; + mic->bridge.driver_private = mic; + ret = drm_bridge_add(&mic->bridge); + if (ret) + DRM_ERROR("mic: Failed to add MIC to the global bridge list\n"); + + return ret; +} + +static void exynos_mic_unbind(struct device *dev, struct device *master, + void *data) +{ + struct exynos_mic *mic = dev_get_drvdata(dev); int i; mutex_lock(&mic_mutex); @@ -387,13 +412,13 @@ void mic_destroy(struct drm_bridge *bridge) already_disabled: mutex_unlock(&mic_mutex); + + drm_bridge_remove(&mic->bridge); } -static const struct drm_bridge_funcs mic_bridge_funcs = { - .disable = mic_disable, - .post_disable = mic_post_disable, - .pre_enable = mic_pre_enable, - .enable = mic_enable, +static const struct component_ops exynos_mic_component_ops = { + .bind = exynos_mic_bind, + .unbind = exynos_mic_unbind, }; int exynos_mic_probe(struct platform_device *pdev) @@ -435,15 +460,6 @@ int exynos_mic_probe(struct platform_device *pdev) goto err; } - mic->bridge.funcs = &mic_bridge_funcs; - mic->bridge.of_node = dev->of_node; - mic->bridge.driver_private = mic; - ret = drm_bridge_add(&mic->bridge); - if (ret) { - DRM_ERROR("mic: Failed to add MIC to the global bridge list\n"); - goto err; - } - for (i = 0; i < NUM_CLKS; i++) { mic->clks[i] = devm_clk_get(dev, clk_names[i]); if (IS_ERR(mic->clks[i])) { @@ -454,7 +470,10 @@ int exynos_mic_probe(struct platform_device *pdev) } } + platform_set_drvdata(pdev, mic); + DRM_DEBUG_KMS("MIC has been probed\n"); + return component_add(dev, &exynos_mic_component_ops); err: return ret; @@ -462,10 +481,7 @@ err: static int exynos_mic_remove(struct platform_device *pdev) { - struct exynos_mic *mic = platform_get_drvdata(pdev); - - drm_bridge_remove(&mic->bridge); - + component_del(&pdev->dev, &exynos_mic_component_ops); return 0; } From 8b0be57286642f87a968c00932c3f2ef936f6b7b Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:50 +0100 Subject: [PATCH 154/489] drm/exynos: mic: make all functions static There is no point exposing all internal functions to global kernel name space, so make all internals functions static. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_mic.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c index 899061a35cf6..9869d70e9e54 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_mic.c +++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c @@ -307,9 +307,9 @@ exit: return ret; } -void mic_disable(struct drm_bridge *bridge) { } +static void mic_disable(struct drm_bridge *bridge) { } -void mic_post_disable(struct drm_bridge *bridge) +static void mic_post_disable(struct drm_bridge *bridge) { struct exynos_mic *mic = bridge->driver_private; int i; @@ -329,7 +329,7 @@ already_disabled: mutex_unlock(&mic_mutex); } -void mic_pre_enable(struct drm_bridge *bridge) +static void mic_pre_enable(struct drm_bridge *bridge) { struct exynos_mic *mic = bridge->driver_private; int ret, i; @@ -372,7 +372,7 @@ already_enabled: mutex_unlock(&mic_mutex); } -void mic_enable(struct drm_bridge *bridge) { } +static void mic_enable(struct drm_bridge *bridge) { } static const struct drm_bridge_funcs mic_bridge_funcs = { .disable = mic_disable, @@ -421,7 +421,7 @@ static const struct component_ops exynos_mic_component_ops = { .unbind = exynos_mic_unbind, }; -int exynos_mic_probe(struct platform_device *pdev) +static int exynos_mic_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; struct exynos_mic *mic; From e7ad6606c000bf71df1ed0dcfca91227ce375db3 Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:51 +0100 Subject: [PATCH 155/489] drm/exynos: dsi: restore support for drm bridge This patch fixes issue introduced by commit cf67cc9a29ac19c98bc4fa0e6d14b0c1f592d322 ("drm/exynos: remove struct exynos_drm_display"), which removed assigning of drm bridge to drm encoder. Lack of it caused that no bridge callbacks were called on encoder enable/disable actions. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_dsi.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c index e977a81af2e6..26e81d191f56 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c +++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c @@ -1782,6 +1782,7 @@ static int exynos_dsi_bind(struct device *dev, struct device *master, bridge = of_drm_find_bridge(dsi->bridge_node); if (bridge) { + encoder->bridge = bridge; drm_bridge_attach(drm_dev, bridge); } From c90f950ce3b33a020292c7e7feca644a706265ca Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:53 +0100 Subject: [PATCH 156/489] drm/exynos: exynos5433_decon: fix wrong state assignment in decon_enable Patch ebf3fd403b79ba6561bd1a4bb5a7cacc99da08e5 ("drm/exynos: add pm_runtime to DECON 5433") removed some code from decon_enable() function, but it left set_bit(BIT_SUSPENDED, &ctx->flags) call, which was earlier called only in error path. This patch removes it, what finally lets driver to go out of suspended state. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 1bf6a21130c7..c79331699140 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -402,8 +402,6 @@ static void decon_enable(struct exynos_drm_crtc *crtc) decon_enable_vblank(ctx->crtc); decon_commit(ctx->crtc); - - set_bit(BIT_SUSPENDED, &ctx->flags); } static void decon_disable(struct exynos_drm_crtc *crtc) From 74ebc70622c95b3e767f62b73a3ef624c913e5dd Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Wed, 3 Feb 2016 13:42:54 +0100 Subject: [PATCH 157/489] drm/exynos: exynos5433_decon: fix wrong state in decon_vblank_enable BIT_IRQS_ENABLED was never set because of incorrect test in decon_vlank_enable() function, what resulted in lack of enabling vblank support. This patch fixes this issue. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index c79331699140..107224a61eb3 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -93,7 +93,7 @@ static int decon_enable_vblank(struct exynos_drm_crtc *crtc) if (test_bit(BIT_SUSPENDED, &ctx->flags)) return -EPERM; - if (test_and_set_bit(BIT_IRQS_ENABLED, &ctx->flags)) { + if (!test_and_set_bit(BIT_IRQS_ENABLED, &ctx->flags)) { val = VIDINTCON0_INTEN; if (ctx->out_type == IFTYPE_I80) val |= VIDINTCON0_FRAMEDONE; From d380a1632c4e036d50c898e874a194fd4bf8bdee Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 11 Feb 2016 12:32:07 +0100 Subject: [PATCH 158/489] drm/exynos: fix incorrect cpu address for dma_mmap_attrs() dma_mmap_attrs() should be called with cpu address returned by dma_alloc_attrs(). Existing code however passed pages array base as cpu address. This worked only by a pure luck on ARM architecture. This patch fixes this issue. Signed-off-by: Marek Szyprowski Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos_drm_fbdev.c | 2 +- drivers/gpu/drm/exynos/exynos_drm_gem.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index f6118baa8e3e..8baabd813ff5 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -50,7 +50,7 @@ static int exynos_drm_fb_mmap(struct fb_info *info, if (vm_size > exynos_gem->size) return -EINVAL; - ret = dma_mmap_attrs(helper->dev->dev, vma, exynos_gem->pages, + ret = dma_mmap_attrs(helper->dev->dev, vma, exynos_gem->cookie, exynos_gem->dma_addr, exynos_gem->size, &exynos_gem->dma_attrs); if (ret < 0) { diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c index 47d126ab6e07..26b5e4bd55b6 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gem.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c @@ -335,7 +335,7 @@ static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem, if (vm_size > exynos_gem->size) return -EINVAL; - ret = dma_mmap_attrs(drm_dev->dev, vma, exynos_gem->pages, + ret = dma_mmap_attrs(drm_dev->dev, vma, exynos_gem->cookie, exynos_gem->dma_addr, exynos_gem->size, &exynos_gem->dma_attrs); if (ret < 0) { From 00780f3b1a10d1be006b920505faf1d02f76f0e4 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Thu, 11 Feb 2016 12:25:04 +0100 Subject: [PATCH 159/489] drm/exynos/decon: fix disable clocks order Decon requires that clocks should be disabled in reverse order. Otherwise system hangs. Signed-off-by: Andrzej Hajda Signed-off-by: Inki Dae --- drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c index 107224a61eb3..162ab93e99cb 100644 --- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c +++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c @@ -580,9 +580,9 @@ out: static int exynos5433_decon_suspend(struct device *dev) { struct decon_context *ctx = dev_get_drvdata(dev); - int i; + int i = ARRAY_SIZE(decon_clks_name); - for (i = 0; i < ARRAY_SIZE(decon_clks_name); i++) + while (--i >= 0) clk_disable_unprepare(ctx->clks[i]); return 0; From 4d8c8bd6f2062c9988817183a91fe2e623c8aa5e Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Thu, 11 Feb 2016 16:10:26 -0500 Subject: [PATCH 160/489] xen/pcifront: Fix mysterious crashes when NUMA locality information was extracted. Occasionaly PV guests would crash with: pciback 0000:00:00.1: Xen PCI mapped GSI0 to IRQ16 BUG: unable to handle kernel paging request at 0000000d1a8c0be0 .. snip.. ] find_next_bit+0xb/0x10 [] cpumask_next_and+0x22/0x40 [] pci_device_probe+0xb8/0x120 [] ? driver_sysfs_add+0x77/0xa0 [] driver_probe_device+0x1a4/0x2d0 [] ? pci_match_device+0xdd/0x110 [] __device_attach_driver+0xa7/0xb0 [] ? __driver_attach+0xa0/0xa0 [] bus_for_each_drv+0x62/0x90 [] __device_attach+0xbd/0x110 [] device_attach+0xb/0x10 [] pci_bus_add_device+0x3c/0x70 [] pci_bus_add_devices+0x38/0x80 [] pcifront_scan_root+0x13e/0x1a0 [] pcifront_backend_changed+0x262/0x60b [] ? xenbus_gather+0xd6/0x160 [] ? put_object+0x2f/0x50 [] xenbus_otherend_changed+0x9d/0xa0 [] backend_changed+0xe/0x10 [] xenwatch_thread+0xc8/0x190 [] ? woken_wake_function+0x10/0x10 which was the result of two things: When we call pci_scan_root_bus we would pass in 'sd' (sysdata) pointer which was an 'pcifront_sd' structure. However in the pci_device_add it expects that the 'sd' is 'struct sysdata' and sets the dev->node to what is in sd->node (offset 4): set_dev_node(&dev->dev, pcibus_to_node(bus)); __pcibus_to_node(const struct pci_bus *bus) { const struct pci_sysdata *sd = bus->sysdata; return sd->node; } However our structure was pcifront_sd which had nothing at that offset: struct pcifront_sd { int domain; /* 0 4 */ /* XXX 4 bytes hole, try to pack */ struct pcifront_device * pdev; /* 8 8 */ } That is an hole - filled with garbage as we used kmalloc instead of kzalloc (the second problem). This patch fixes the issue by: 1) Use kzalloc to initialize to a well known state. 2) Put 'struct pci_sysdata' at the start of 'pcifront_sd'. That way access to the 'node' will access the right offset. Signed-off-by: Konrad Rzeszutek Wilk Cc: Reviewed-by: Boris Ostrovsky Signed-off-by: David Vrabel --- drivers/pci/xen-pcifront.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index c777b97207d5..5f70fee59a94 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -53,7 +53,7 @@ struct pcifront_device { }; struct pcifront_sd { - int domain; + struct pci_sysdata sd; struct pcifront_device *pdev; }; @@ -67,7 +67,9 @@ static inline void pcifront_init_sd(struct pcifront_sd *sd, unsigned int domain, unsigned int bus, struct pcifront_device *pdev) { - sd->domain = domain; + /* Because we do not expose that information via XenBus. */ + sd->sd.node = first_online_node; + sd->sd.domain = domain; sd->pdev = pdev; } @@ -468,8 +470,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev, dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n", domain, bus); - bus_entry = kmalloc(sizeof(*bus_entry), GFP_KERNEL); - sd = kmalloc(sizeof(*sd), GFP_KERNEL); + bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL); + sd = kzalloc(sizeof(*sd), GFP_KERNEL); if (!bus_entry || !sd) { err = -ENOMEM; goto err_out; From d99a36f4728fcbcc501b78447f625bdcce15b842 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 15 Feb 2016 16:20:24 +0100 Subject: [PATCH 161/489] ALSA: seq: Fix leak of pool buffer at concurrent writes When multiple concurrent writes happen on the ALSA sequencer device right after the open, it may try to allocate vmalloc buffer for each write and leak some of them. It's because the presence check and the assignment of the buffer is done outside the spinlock for the pool. The fix is to move the check and the assignment into the spinlock. (The current implementation is suboptimal, as there can be multiple unnecessary vmallocs because the allocation is done before the check in the spinlock. But the pool size is already checked beforehand, so this isn't a big problem; that is, the only possible path is the multiple writes before any pool assignment, and practically seen, the current coverage should be "good enough".) The issue was triggered by syzkaller fuzzer. BugLink: http://lkml.kernel.org/r/CACT4Y+bSzazpXNvtAr=WXaL8hptqjHwqEyFA+VN2AWEx=aurkg@mail.gmail.com Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Cc: Signed-off-by: Takashi Iwai --- sound/core/seq/seq_memory.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c index 801076687bb1..c850345c43b5 100644 --- a/sound/core/seq/seq_memory.c +++ b/sound/core/seq/seq_memory.c @@ -383,15 +383,20 @@ int snd_seq_pool_init(struct snd_seq_pool *pool) if (snd_BUG_ON(!pool)) return -EINVAL; - if (pool->ptr) /* should be atomic? */ - return 0; - pool->ptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); - if (!pool->ptr) + cellptr = vmalloc(sizeof(struct snd_seq_event_cell) * pool->size); + if (!cellptr) return -ENOMEM; /* add new cells to the free cell list */ spin_lock_irqsave(&pool->lock, flags); + if (pool->ptr) { + spin_unlock_irqrestore(&pool->lock, flags); + vfree(cellptr); + return 0; + } + + pool->ptr = cellptr; pool->free = NULL; for (cell = 0; cell < pool->size; cell++) { From 0b8c82190c12e530eb6003720dac103bf63e146e Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 15 Feb 2016 16:37:24 +0100 Subject: [PATCH 162/489] ALSA: hda - Cancel probe work instead of flush at remove The commit [991f86d7ae4e: ALSA: hda - Flush the pending probe work at remove] introduced the sync of async probe work at remove for fixing the race. However, this may lead to another hangup when the module removal is performed quickly before starting the probe work, because it issues flush_work() and it's blocked forever. The workaround is to use cancel_work_sync() instead of flush_work() there. Fixes: 991f86d7ae4e ('ALSA: hda - Flush the pending probe work at remove') Cc: # v3.17+ Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 4045dca3d699..ce6b97f31390 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2168,10 +2168,10 @@ static void azx_remove(struct pci_dev *pci) struct hda_intel *hda; if (card) { - /* flush the pending probing work */ + /* cancel the pending probing work */ chip = card->private_data; hda = container_of(chip, struct hda_intel, chip); - flush_work(&hda->probe_work); + cancel_work_sync(&hda->probe_work); snd_card_free(card); } From bee038a4bd2efe8188cc80dfdad706a9abe568ad Mon Sep 17 00:00:00 2001 From: Jeremy Linton Date: Fri, 12 Feb 2016 09:47:52 -0600 Subject: [PATCH 163/489] arm/arm64: crypto: assure that ECB modes don't require an IV ECB modes don't use an initialization vector. The kernel /proc/crypto interface doesn't reflect this properly. Acked-by: Ard Biesheuvel Signed-off-by: Jeremy Linton Signed-off-by: Will Deacon --- arch/arm/crypto/aes-ce-glue.c | 4 ++-- arch/arm64/crypto/aes-glue.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index b445a5d56f43..89a3a3e592d6 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -364,7 +364,7 @@ static struct crypto_alg aes_algs[] = { { .cra_blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = ce_aes_setkey, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, @@ -441,7 +441,7 @@ static struct crypto_alg aes_algs[] = { { .cra_ablkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = ablk_set_key, .encrypt = ablk_encrypt, .decrypt = ablk_decrypt, diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c index 05d9e16c0dfd..7a3d22a46faf 100644 --- a/arch/arm64/crypto/aes-glue.c +++ b/arch/arm64/crypto/aes-glue.c @@ -294,7 +294,7 @@ static struct crypto_alg aes_algs[] = { { .cra_blkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = aes_setkey, .encrypt = ecb_encrypt, .decrypt = ecb_decrypt, @@ -371,7 +371,7 @@ static struct crypto_alg aes_algs[] = { { .cra_ablkcipher = { .min_keysize = AES_MIN_KEY_SIZE, .max_keysize = AES_MAX_KEY_SIZE, - .ivsize = AES_BLOCK_SIZE, + .ivsize = 0, .setkey = ablk_set_key, .encrypt = ablk_encrypt, .decrypt = ablk_decrypt, From ee1cdcdae59563535485a5f56ee72c894ab7d7ad Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 10 Feb 2016 15:59:42 +0200 Subject: [PATCH 164/489] dmaengine: dw: disable BLOCK IRQs for non-cyclic xfer The commit 2895b2cad6e7 ("dmaengine: dw: fix cyclic transfer callbacks") re-enabled BLOCK interrupts with regard to make cyclic transfers work. However, this change becomes a regression for non-cyclic transfers as interrupt counters under stress test had been grown enormously (approximately per 4-5 bytes in the UART loop back test). Taking into consideration above enable BLOCK interrupts if and only if channel is programmed to perform cyclic transfer. Fixes: 2895b2cad6e7 ("dmaengine: dw: fix cyclic transfer callbacks") Signed-off-by: Andy Shevchenko Acked-by: Mans Rullgard Tested-by: Mans Rullgard Acked-by: Viresh Kumar Cc: Signed-off-by: Vinod Koul --- drivers/dma/dw/core.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index e893318560db..5ad0ec1f0e29 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -156,7 +156,6 @@ static void dwc_initialize(struct dw_dma_chan *dwc) /* Enable interrupts */ channel_set_bit(dw, MASK.XFER, dwc->mask); - channel_set_bit(dw, MASK.BLOCK, dwc->mask); channel_set_bit(dw, MASK.ERROR, dwc->mask); dwc->initialized = true; @@ -588,6 +587,9 @@ static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc, spin_unlock_irqrestore(&dwc->lock, flags); } + + /* Re-enable interrupts */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); } /* ------------------------------------------------------------------------- */ @@ -618,11 +620,8 @@ static void dw_dma_tasklet(unsigned long data) dwc_scan_descriptors(dw, dwc); } - /* - * Re-enable interrupts. - */ + /* Re-enable interrupts */ channel_set_bit(dw, MASK.XFER, dw->all_chan_mask); - channel_set_bit(dw, MASK.BLOCK, dw->all_chan_mask); channel_set_bit(dw, MASK.ERROR, dw->all_chan_mask); } @@ -1261,6 +1260,7 @@ static void dwc_free_chan_resources(struct dma_chan *chan) int dw_dma_cyclic_start(struct dma_chan *chan) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(chan->device); unsigned long flags; if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) { @@ -1269,7 +1269,12 @@ int dw_dma_cyclic_start(struct dma_chan *chan) } spin_lock_irqsave(&dwc->lock, flags); + + /* Enable interrupts to perform cyclic transfer */ + channel_set_bit(dw, MASK.BLOCK, dwc->mask); + dwc_dostart(dwc, dwc->cdesc->desc[0]); + spin_unlock_irqrestore(&dwc->lock, flags); return 0; From 2f21596882f4a0edc387051910d56f8732970080 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 15 Feb 2016 12:36:04 -0500 Subject: [PATCH 165/489] pNFS: Fix pnfs_mark_matching_lsegs_return() We don't need to schedule a layoutreturn if the layout segment can be freed immediately. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 482b6e94bb37..8d9fa4e40e89 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1740,6 +1740,16 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) lo->plh_return_iomode = iomode; } +/** + * pnfs_mark_matching_lsegs_return - Free or return matching layout segments + * @lo: pointer to layout header + * @tmp_list: list header to be used with pnfs_free_lseg_list() + * @return_range: describe layout segment ranges to be returned + * + * This function is mainly intended for use by layoutrecall. It attempts + * to free the layout segment immediately, or else to mark it for return + * as soon as its reference count drops to zero. + */ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, struct list_head *tmp_list, @@ -1762,10 +1772,11 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, lseg, lseg->pls_range.iomode, lseg->pls_range.offset, lseg->pls_range.length); + if (mark_lseg_invalid(lseg, tmp_list)) + continue; + remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); pnfs_set_plh_return_iomode(lo, return_range->iomode); - if (!mark_lseg_invalid(lseg, tmp_list)) - remaining++; set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } From e0fa0d0189f6be61343dbff1f71bef20125576e7 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 15 Feb 2016 12:56:17 -0500 Subject: [PATCH 166/489] pNFS: Always set NFS_LAYOUT_RETURN_REQUESTED with lo->plh_return_iomode When setting the layout return mode, we must always also set the NFS_LAYOUT_RETURN_REQUESTED flag to ensure that we send a layoutreturn. Otherwise pnfs_error_mark_layout_for_return() could set the mode, but fail to send the layoutreturn because another is already in flight. Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8d9fa4e40e89..5064f23ca8cc 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1738,6 +1738,7 @@ pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode) if (lo->plh_return_iomode != 0) iomode = IOMODE_ANY; lo->plh_return_iomode = iomode; + set_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags); } /** @@ -1777,8 +1778,6 @@ pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, remaining++; set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags); pnfs_set_plh_return_iomode(lo, return_range->iomode); - set_bit(NFS_LAYOUT_RETURN_REQUESTED, - &lo->plh_flags); } return remaining; } From f37755490fe9bf76f6ba1d8c6591745d3574a6a6 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 15 Feb 2016 12:36:14 -0500 Subject: [PATCH 167/489] tracepoints: Do not trace when cpu is offline The tracepoint infrastructure uses RCU sched protection to enable and disable tracepoints safely. There are some instances where tracepoints are used in infrastructure code (like kfree()) that get called after a CPU is going offline, and perhaps when it is coming back online but hasn't been registered yet. This can probuce the following warning: [ INFO: suspicious RCU usage. ] 4.4.0-00006-g0fe53e8-dirty #34 Tainted: G S ------------------------------- include/trace/events/kmem.h:141 suspicious rcu_dereference_check() usage! other info that might help us debug this: RCU used illegally from offline CPU! rcu_scheduler_active = 1, debug_locks = 1 no locks held by swapper/8/0. stack backtrace: CPU: 8 PID: 0 Comm: swapper/8 Tainted: G S 4.4.0-00006-g0fe53e8-dirty #34 Call Trace: [c0000005b76c78d0] [c0000000008b9540] .dump_stack+0x98/0xd4 (unreliable) [c0000005b76c7950] [c00000000010c898] .lockdep_rcu_suspicious+0x108/0x170 [c0000005b76c79e0] [c00000000029adc0] .kfree+0x390/0x440 [c0000005b76c7a80] [c000000000055f74] .destroy_context+0x44/0x100 [c0000005b76c7b00] [c0000000000934a0] .__mmdrop+0x60/0x150 [c0000005b76c7b90] [c0000000000e3ff0] .idle_task_exit+0x130/0x140 [c0000005b76c7c20] [c000000000075804] .pseries_mach_cpu_die+0x64/0x310 [c0000005b76c7cd0] [c000000000043e7c] .cpu_die+0x3c/0x60 [c0000005b76c7d40] [c0000000000188d8] .arch_cpu_idle_dead+0x28/0x40 [c0000005b76c7db0] [c000000000101e6c] .cpu_startup_entry+0x50c/0x560 [c0000005b76c7ed0] [c000000000043bd8] .start_secondary+0x328/0x360 [c0000005b76c7f90] [c000000000008a6c] start_secondary_prolog+0x10/0x14 This warning is not a false positive either. RCU is not protecting code that is being executed while the CPU is offline. Instead of playing "whack-a-mole(TM)" and adding conditional statements to the tracepoints we find that are used in this instance, simply add a cpu_online() test to the tracepoint code where the tracepoint will be ignored if the CPU is offline. Use of raw_smp_processor_id() is fine, as there should never be a case where the tracepoint code goes from running on a CPU that is online and suddenly gets migrated to a CPU that is offline. Link: http://lkml.kernel.org/r/1455387773-4245-1-git-send-email-kda@linux-powerpc.org Reported-by: Denis Kirjanov Fixes: 97e1c18e8d17b ("tracing: Kernel Tracepoints") Cc: stable@vger.kernel.org # v2.6.28+ Signed-off-by: Steven Rostedt --- include/linux/tracepoint.h | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index acd522a91539..acfdbf353a0b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -14,8 +14,10 @@ * See the file COPYING for more details. */ +#include #include #include +#include #include #include @@ -132,6 +134,9 @@ extern void syscall_unregfunc(void); void *it_func; \ void *__data; \ \ + if (!cpu_online(raw_smp_processor_id())) \ + return; \ + \ if (!(cond)) \ return; \ prercu; \ From b33c8ff4431a343561e2319f17c14286f2aa52e2 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 12 Feb 2016 22:26:42 +0100 Subject: [PATCH 168/489] tracing: Fix freak link error caused by branch tracer In my randconfig tests, I came across a bug that involves several components: * gcc-4.9 through at least 5.3 * CONFIG_GCOV_PROFILE_ALL enabling -fprofile-arcs for all files * CONFIG_PROFILE_ALL_BRANCHES overriding every if() * The optimized implementation of do_div() that tries to replace a library call with an division by multiplication * code in drivers/media/dvb-frontends/zl10353.c doing u32 adc_clock = 450560; /* 45.056 MHz */ if (state->config.adc_clock) adc_clock = state->config.adc_clock; do_div(value, adc_clock); In this case, gcc fails to determine whether the divisor in do_div() is __builtin_constant_p(). In particular, it concludes that __builtin_constant_p(adc_clock) is false, while __builtin_constant_p(!!adc_clock) is true. That in turn throws off the logic in do_div() that also uses __builtin_constant_p(), and instead of picking either the constant- optimized division, and the code in ilog2() that uses __builtin_constant_p() to figure out whether it knows the answer at compile time. The result is a link error from failing to find multiple symbols that should never have been called based on the __builtin_constant_p(): dvb-frontends/zl10353.c:138: undefined reference to `____ilog2_NaN' dvb-frontends/zl10353.c:138: undefined reference to `__aeabi_uldivmod' ERROR: "____ilog2_NaN" [drivers/media/dvb-frontends/zl10353.ko] undefined! ERROR: "__aeabi_uldivmod" [drivers/media/dvb-frontends/zl10353.ko] undefined! This patch avoids the problem by changing __trace_if() to check whether the condition is known at compile-time to be nonzero, rather than checking whether it is actually a constant. I see this one link error in roughly one out of 1600 randconfig builds on ARM, and the patch fixes all known instances. Link: http://lkml.kernel.org/r/1455312410-1058841-1-git-send-email-arnd@arndb.de Acked-by: Nicolas Pitre Fixes: ab3c9c686e22 ("branch tracer, intel-iommu: fix build with CONFIG_BRANCH_TRACER=y") Cc: stable@vger.kernel.org # v2.6.30+ Signed-off-by: Arnd Bergmann Signed-off-by: Steven Rostedt --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 00b042c49ccd..48f5aab117ae 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -144,7 +144,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); */ #define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) ) #define __trace_if(cond) \ - if (__builtin_constant_p((cond)) ? !!(cond) : \ + if (__builtin_constant_p(!!(cond)) ? !!(cond) : \ ({ \ int ______r; \ static struct ftrace_branch_data \ From d9ff0eb9ca4b00ce2fbf9ede1e99681f05c0bc91 Mon Sep 17 00:00:00 2001 From: Youngmin Nam Date: Tue, 9 Feb 2016 00:49:28 +0900 Subject: [PATCH 169/489] pinctrl: samsung: fix SMP race condition Previously, samsung_gpio_drection_in/output function were not covered with a spinlock. For example, samsung_gpio_direction_output function consists of two functions. 1. samsung_gpio_set 2. samsung_gpio_set_direction When 2 CPUs try to control the same gpio pin heavily, (situation like i2c control with gpio emulation) This situation can cause below problem. CPU 0 | CPU1 | samsung_gpio_direction_output | samsung_gpio_set(pin A as 1) | samsung_gpio_direction_output | samsung_gpio_set(pin A as 0) samsung_gpio_set_direction | | samsung_gpio_set_direction The initial value of pin A will be set as 0 while we wanted to set pin A as 1. This patch modifies samsung_gpio_direction_in/output function to be done in one spinlock to fix race condition. Additionally, the new samsung_gpio_set_value was added to implement gpio set callback(samsung_gpio_set) with spinlock using this function. Cc: stable@vger.kernel.org Signed-off-by: Youngmin Nam Acked-by: Tomasz Figa Signed-off-by: Linus Walleij --- drivers/pinctrl/samsung/pinctrl-samsung.c | 48 +++++++++++++++++------ 1 file changed, 35 insertions(+), 13 deletions(-) diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c index f67b1e958589..5cc97f85db02 100644 --- a/drivers/pinctrl/samsung/pinctrl-samsung.c +++ b/drivers/pinctrl/samsung/pinctrl-samsung.c @@ -514,25 +514,35 @@ static const struct pinconf_ops samsung_pinconf_ops = { .pin_config_group_set = samsung_pinconf_group_set, }; -/* gpiolib gpio_set callback function */ -static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value) +/* + * The samsung_gpio_set_vlaue() should be called with "bank->slock" held + * to avoid race condition. + */ +static void samsung_gpio_set_value(struct gpio_chip *gc, + unsigned offset, int value) { struct samsung_pin_bank *bank = gpiochip_get_data(gc); const struct samsung_pin_bank_type *type = bank->type; - unsigned long flags; void __iomem *reg; u32 data; reg = bank->drvdata->virt_base + bank->pctl_offset; - spin_lock_irqsave(&bank->slock, flags); - data = readl(reg + type->reg_offset[PINCFG_TYPE_DAT]); data &= ~(1 << offset); if (value) data |= 1 << offset; writel(data, reg + type->reg_offset[PINCFG_TYPE_DAT]); +} +/* gpiolib gpio_set callback function */ +static void samsung_gpio_set(struct gpio_chip *gc, unsigned offset, int value) +{ + struct samsung_pin_bank *bank = gpiochip_get_data(gc); + unsigned long flags; + + spin_lock_irqsave(&bank->slock, flags); + samsung_gpio_set_value(gc, offset, value); spin_unlock_irqrestore(&bank->slock, flags); } @@ -553,6 +563,8 @@ static int samsung_gpio_get(struct gpio_chip *gc, unsigned offset) } /* + * The samsung_gpio_set_direction() should be called with "bank->slock" held + * to avoid race condition. * The calls to gpio_direction_output() and gpio_direction_input() * leads to this function call. */ @@ -564,7 +576,6 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc, struct samsung_pinctrl_drv_data *drvdata; void __iomem *reg; u32 data, mask, shift; - unsigned long flags; bank = gpiochip_get_data(gc); type = bank->type; @@ -581,31 +592,42 @@ static int samsung_gpio_set_direction(struct gpio_chip *gc, reg += 4; } - spin_lock_irqsave(&bank->slock, flags); - data = readl(reg); data &= ~(mask << shift); if (!input) data |= FUNC_OUTPUT << shift; writel(data, reg); - spin_unlock_irqrestore(&bank->slock, flags); - return 0; } /* gpiolib gpio_direction_input callback function. */ static int samsung_gpio_direction_input(struct gpio_chip *gc, unsigned offset) { - return samsung_gpio_set_direction(gc, offset, true); + struct samsung_pin_bank *bank = gpiochip_get_data(gc); + unsigned long flags; + int ret; + + spin_lock_irqsave(&bank->slock, flags); + ret = samsung_gpio_set_direction(gc, offset, true); + spin_unlock_irqrestore(&bank->slock, flags); + return ret; } /* gpiolib gpio_direction_output callback function. */ static int samsung_gpio_direction_output(struct gpio_chip *gc, unsigned offset, int value) { - samsung_gpio_set(gc, offset, value); - return samsung_gpio_set_direction(gc, offset, false); + struct samsung_pin_bank *bank = gpiochip_get_data(gc); + unsigned long flags; + int ret; + + spin_lock_irqsave(&bank->slock, flags); + samsung_gpio_set_value(gc, offset, value); + ret = samsung_gpio_set_direction(gc, offset, false); + spin_unlock_irqrestore(&bank->slock, flags); + + return ret; } /* From 1636d1d77ef4e01e57f706a4cae3371463896136 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 15 Feb 2016 16:20:26 +0000 Subject: [PATCH 170/489] Btrfs: fix direct IO requests not reporting IO error to user space If a bio for a direct IO request fails, we were not setting the error in the parent bio (the main DIO bio), making us not return the error to user space in btrfs_direct_IO(), that is, it made __blockdev_direct_IO() return the number of bytes issued for IO and not the error a bio created and submitted by btrfs_submit_direct() got from the block layer. This essentially happens because when we call: dio_end_io(dio_bio, bio->bi_error); It does not set dio_bio->bi_error to the value of the second argument. So just add this missing assignment in endio callbacks, just as we do in the error path at btrfs_submit_direct() when we fail to clone the dio bio or allocate its private object. This follows the convention of what is done with other similar APIs such as bio_endio() where the caller is responsible for setting the bi_error field in the bio it passes as an argument to bio_endio(). This was detected by the new generic test cases in xfstests: 271, 272, 276 and 278. Which essentially setup a dm error target, then load the error table, do a direct IO write and unload the error table. They expect the write to fail with -EIO, which was not getting reported when testing against btrfs. Cc: stable@vger.kernel.org # 4.3+ Fixes: 4246a0b63bd8 ("block: add a bi_error field to struct bio") Signed-off-by: Filipe Manana --- fs/btrfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 600bf0d9ceaf..e0ad8b2c2a36 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7985,6 +7985,7 @@ static void btrfs_endio_direct_read(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); if (io_bio->end_io) @@ -8039,6 +8040,7 @@ static void btrfs_endio_direct_write(struct bio *bio) kfree(dip); + dio_bio->bi_error = bio->bi_error; dio_end_io(dio_bio, bio->bi_error); bio_put(bio); } From c906f38e8853cfd407b30d2f4756a93c1d8f698f Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Tue, 16 Feb 2016 00:20:19 -0500 Subject: [PATCH 171/489] ext4: fix memleak in ext4_readdir() When ext4_bread() fails, fname_crypto_str remains allocated after return. Fix that. Signed-off-by: Kirill Tkhai Signed-off-by: Theodore Ts'o CC: Dmitry Monakhov --- fs/ext4/dir.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 6d17f31a31d7..33f5e2a50cf8 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -163,8 +163,11 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) index, 1); file->f_ra.prev_pos = (loff_t)index << PAGE_CACHE_SHIFT; bh = ext4_bread(NULL, inode, map.m_lblk, 0); - if (IS_ERR(bh)) - return PTR_ERR(bh); + if (IS_ERR(bh)) { + err = PTR_ERR(bh); + bh = NULL; + goto errout; + } } if (!bh) { From c18bdd018e8912ca73ad6c12120b7283b5038875 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 31 Jan 2016 13:27:59 +0100 Subject: [PATCH 172/489] batman-adv: Only put gw_node list reference when removed The batadv_gw_node reference counter in batadv_gw_node_update can only be reduced when the list entry was actually removed. Otherwise the reference counter may reach zero when batadv_gw_node_update is called from two different contexts for the same gw_node but only one context is actually removing the entry from the list. The release function for this gw_node is not called inside the list_lock spinlock protected region because the function batadv_gw_node_update still holds a gw_node reference for the object pointer on the stack. Thus the actual release function (when required) will be called only at the end of the function. Fixes: bd3524c14bd0 ("batman-adv: remove obsolete deleted attribute for gateway node") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli --- net/batman-adv/gateway_client.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index e6c8382c79ba..ccf70bed0d0c 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -527,11 +527,12 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv, * gets dereferenced. */ spin_lock_bh(&bat_priv->gw.list_lock); - hlist_del_init_rcu(&gw_node->list); + if (!hlist_unhashed(&gw_node->list)) { + hlist_del_init_rcu(&gw_node->list); + batadv_gw_node_free_ref(gw_node); + } spin_unlock_bh(&bat_priv->gw.list_lock); - batadv_gw_node_free_ref(gw_node); - curr_gw = batadv_gw_get_selected_gw_node(bat_priv); if (gw_node == curr_gw) batadv_gw_reselect(bat_priv); From 3db152093efb750bc47fd4d69355b90b18113105 Mon Sep 17 00:00:00 2001 From: Sven Eckelmann Date: Sun, 31 Jan 2016 13:28:00 +0100 Subject: [PATCH 173/489] batman-adv: Only put orig_node_vlan list reference when removed The batadv_orig_node_vlan reference counter in batadv_tt_global_size_mod can only be reduced when the list entry was actually removed. Otherwise the reference counter may reach zero when batadv_tt_global_size_mod is called from two different contexts for the same orig_node_vlan but only one context is actually removing the entry from the list. The release function for this orig_node_vlan is not called inside the vlan_list_lock spinlock protected region because the function batadv_tt_global_size_mod still holds a orig_node_vlan reference for the object pointer on the stack. Thus the actual release function (when required) will be called only at the end of the function. Fixes: 7ea7b4a14275 ("batman-adv: make the TT CRC logic VLAN specific") Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli --- net/batman-adv/translation-table.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index cdfc85fa2743..0e80fd1461ab 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -303,9 +303,11 @@ static void batadv_tt_global_size_mod(struct batadv_orig_node *orig_node, if (atomic_add_return(v, &vlan->tt.num_entries) == 0) { spin_lock_bh(&orig_node->vlan_list_lock); - hlist_del_init_rcu(&vlan->list); + if (!hlist_unhashed(&vlan->list)) { + hlist_del_init_rcu(&vlan->list); + batadv_orig_node_vlan_free_ref(vlan); + } spin_unlock_bh(&orig_node->vlan_list_lock); - batadv_orig_node_vlan_free_ref(vlan); } batadv_orig_node_vlan_free_ref(vlan); From 7f4e346263f59ff50b531dda94609fb13ca12401 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Tue, 16 Feb 2016 11:16:31 +0100 Subject: [PATCH 174/489] arm64/efi: Make strnlen() available to the EFI namespace Changes introduced in the upstream version of libfdt pulled in by commit 91feabc2e224 ("scripts/dtc: Update to upstream commit b06e55c88b9b") use the strnlen() function, which isn't currently available to the EFI name- space. Add it to the EFI namespace to avoid a linker error. Cc: Catalin Marinas Cc: Rob Herring Reviewed-by: Ard Biesheuvel Signed-off-by: Thierry Reding Signed-off-by: Will Deacon --- arch/arm64/kernel/image.h | 1 + arch/arm64/lib/strnlen.S | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kernel/image.h b/arch/arm64/kernel/image.h index 999633bd7294..352f7abd91c9 100644 --- a/arch/arm64/kernel/image.h +++ b/arch/arm64/kernel/image.h @@ -89,6 +89,7 @@ __efistub_memcpy = KALLSYMS_HIDE(__pi_memcpy); __efistub_memmove = KALLSYMS_HIDE(__pi_memmove); __efistub_memset = KALLSYMS_HIDE(__pi_memset); __efistub_strlen = KALLSYMS_HIDE(__pi_strlen); +__efistub_strnlen = KALLSYMS_HIDE(__pi_strnlen); __efistub_strcmp = KALLSYMS_HIDE(__pi_strcmp); __efistub_strncmp = KALLSYMS_HIDE(__pi_strncmp); __efistub___flush_dcache_area = KALLSYMS_HIDE(__pi___flush_dcache_area); diff --git a/arch/arm64/lib/strnlen.S b/arch/arm64/lib/strnlen.S index 2ca665711bf2..eae38da6e0bb 100644 --- a/arch/arm64/lib/strnlen.S +++ b/arch/arm64/lib/strnlen.S @@ -168,4 +168,4 @@ CPU_LE( lsr tmp2, tmp2, tmp4 ) /* Shift (tmp1 & 63). */ .Lhit_limit: mov len, limit ret -ENDPROC(strnlen) +ENDPIPROC(strnlen) From e246eb568bc4cbbdd8a30a3c11151ff9b7ca7312 Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Mon, 15 Feb 2016 10:34:05 +0000 Subject: [PATCH 175/489] efi: Add pstore variables to the deletion whitelist Laszlo explains why this is a good idea, 'This is because the pstore filesystem can be backed by UEFI variables, and (for example) a crash might dump the last kilobytes of the dmesg into a number of pstore entries, each entry backed by a separate UEFI variable in the above GUID namespace, and with a variable name according to the above pattern. Please see "drivers/firmware/efi/efi-pstore.c". While this patch series will not prevent the user from deleting those UEFI variables via the pstore filesystem (i.e., deleting a pstore fs entry will continue to delete the backing UEFI variable), I think it would be nice to preserve the possibility for the sysadmin to delete Linux-created UEFI variables that carry portions of the crash log, *without* having to mount the pstore filesystem.' There's also no chance of causing machines to become bricked by deleting these variables, which is the whole purpose of excluding things from the whitelist. Use the LINUX_EFI_CRASH_GUID guid and a wildcard '*' for the match so that we don't have to update the string in the future if new variable name formats are created for crash dump variables. Reported-by: Laszlo Ersek Acked-by: Peter Jones Tested-by: Peter Jones Cc: Matthew Garrett Cc: "Lee, Chun-Yi" Signed-off-by: Matt Fleming --- drivers/firmware/efi/vars.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/firmware/efi/vars.c b/drivers/firmware/efi/vars.c index 50f10bad2604..7f2ea21c730d 100644 --- a/drivers/firmware/efi/vars.c +++ b/drivers/firmware/efi/vars.c @@ -198,6 +198,7 @@ static const struct variable_validate variable_validate[] = { { EFI_GLOBAL_VARIABLE_GUID, "OsIndications", NULL }, { EFI_GLOBAL_VARIABLE_GUID, "PlatformLang", validate_ascii_string }, { EFI_GLOBAL_VARIABLE_GUID, "Timeout", validate_uint16 }, + { LINUX_EFI_CRASH_GUID, "*", NULL }, { NULL_GUID, "", NULL }, }; From a68075908a37850918ad96b056acc9ac4ce1bd90 Mon Sep 17 00:00:00 2001 From: Jason Andryuk Date: Fri, 12 Feb 2016 23:13:33 +0000 Subject: [PATCH 176/489] lib/ucs2_string: Correct ucs2 -> utf8 conversion The comparisons should be >= since 0x800 and 0x80 require an additional bit to store. For the 3 byte case, the existing shift would drop off 2 more bits than intended. For the 2 byte case, there should be 5 bits bits in byte 1, and 6 bits in byte 2. Signed-off-by: Jason Andryuk Reviewed-by: Laszlo Ersek Cc: Peter Jones Cc: Matthew Garrett Cc: "Lee, Chun-Yi" Signed-off-by: Matt Fleming --- lib/ucs2_string.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/lib/ucs2_string.c b/lib/ucs2_string.c index 17dd74e21ef9..f0b323abb4c6 100644 --- a/lib/ucs2_string.c +++ b/lib/ucs2_string.c @@ -59,9 +59,9 @@ ucs2_utf8size(const ucs2_char_t *src) for (i = 0; i < ucs2_strlen(src); i++) { u16 c = src[i]; - if (c > 0x800) + if (c >= 0x800) j += 3; - else if (c > 0x80) + else if (c >= 0x80) j += 2; else j += 1; @@ -88,19 +88,19 @@ ucs2_as_utf8(u8 *dest, const ucs2_char_t *src, unsigned long maxlength) for (i = 0; maxlength && i < limit; i++) { u16 c = src[i]; - if (c > 0x800) { + if (c >= 0x800) { if (maxlength < 3) break; maxlength -= 3; dest[j++] = 0xe0 | (c & 0xf000) >> 12; - dest[j++] = 0x80 | (c & 0x0fc0) >> 8; + dest[j++] = 0x80 | (c & 0x0fc0) >> 6; dest[j++] = 0x80 | (c & 0x003f); - } else if (c > 0x80) { + } else if (c >= 0x80) { if (maxlength < 2) break; maxlength -= 2; - dest[j++] = 0xc0 | (c & 0xfe0) >> 5; - dest[j++] = 0x80 | (c & 0x01f); + dest[j++] = 0xc0 | (c & 0x7c0) >> 6; + dest[j++] = 0x80 | (c & 0x03f); } else { maxlength -= 1; dest[j++] = c & 0x7f; From 13d5e5d4725c64ec06040d636832e78453f477b7 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 16 Feb 2016 14:15:59 +0100 Subject: [PATCH 177/489] ALSA: seq: Fix double port list deletion The commit [7f0973e973cd: ALSA: seq: Fix lockdep warnings due to double mutex locks] split the management of two linked lists (source and destination) into two individual calls for avoiding the AB/BA deadlock. However, this may leave the possible double deletion of one of two lists when the counterpart is being deleted concurrently. It ends up with a list corruption, as revealed by syzkaller fuzzer. This patch fixes it by checking the list emptiness and skipping the deletion and the following process. BugLink: http://lkml.kernel.org/r/CACT4Y+bay9qsrz6dQu31EcGaH9XwfW7o3oBzSQUG9fMszoh=Sg@mail.gmail.com Fixes: 7f0973e973cd ('ALSA: seq: Fix lockdep warnings due to 'double mutex locks) Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Cc: Signed-off-by: Takashi Iwai --- sound/core/seq/seq_ports.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/sound/core/seq/seq_ports.c b/sound/core/seq/seq_ports.c index 921fb2bd8fad..fe686ee41c6d 100644 --- a/sound/core/seq/seq_ports.c +++ b/sound/core/seq/seq_ports.c @@ -535,19 +535,22 @@ static void delete_and_unsubscribe_port(struct snd_seq_client *client, bool is_src, bool ack) { struct snd_seq_port_subs_info *grp; + struct list_head *list; + bool empty; grp = is_src ? &port->c_src : &port->c_dest; + list = is_src ? &subs->src_list : &subs->dest_list; down_write(&grp->list_mutex); write_lock_irq(&grp->list_lock); - if (is_src) - list_del(&subs->src_list); - else - list_del(&subs->dest_list); + empty = list_empty(list); + if (!empty) + list_del_init(list); grp->exclusive = 0; write_unlock_irq(&grp->list_lock); up_write(&grp->list_mutex); - unsubscribe_port(client, port, grp, &subs->info, ack); + if (!empty) + unsubscribe_port(client, port, grp, &subs->info, ack); } /* connect two ports */ From 1bc4e2b000e7fa9773d6623bc8850561ce10a4fb Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Thu, 11 Feb 2016 22:15:57 +0100 Subject: [PATCH 178/489] batman-adv: Avoid endless loop in bat-on-bat netdevice check batman-adv checks in different situation if a new device is already on top of a different batman-adv device. This is done by getting the iflink of a device and all its parent. It assumes that this iflink is always a parent device in an acyclic graph. But this assumption is broken by devices like veth which are actually a pair of two devices linked to each other. The recursive check would therefore get veth0 when calling dev_get_iflink on veth1. And it gets veth0 when calling dev_get_iflink with veth1. Creating a veth pair and loading batman-adv freezes parts of the system ip link add veth0 type veth peer name veth1 modprobe batman-adv An RCU stall will be detected on the system which cannot be fixed. INFO: rcu_sched self-detected stall on CPU 1: (5264 ticks this GP) idle=3e9/140000000000001/0 softirq=144683/144686 fqs=5249 (t=5250 jiffies g=46 c=45 q=43) Task dump for CPU 1: insmod R running task 0 247 245 0x00000008 ffffffff8151f140 ffffffff8107888e ffff88000fd141c0 ffffffff8151f140 0000000000000000 ffffffff81552df0 ffffffff8107b420 0000000000000001 ffff88000e3fa700 ffffffff81540b00 ffffffff8107d667 0000000000000001 Call Trace: [] ? rcu_dump_cpu_stacks+0x7e/0xd0 [] ? rcu_check_callbacks+0x3f0/0x6b0 [] ? hrtimer_run_queues+0x47/0x180 [] ? update_process_times+0x2d/0x50 [] ? tick_handle_periodic+0x1b/0x60 [] ? smp_trace_apic_timer_interrupt+0x5e/0x90 [] ? apic_timer_interrupt+0x82/0x90 [] ? __dev_get_by_index+0x37/0x40 [] ? batadv_hard_if_event+0xee/0x3a0 [batman_adv] [] ? register_netdevice_notifier+0x81/0x1a0 [...] This can be avoided by checking if two devices are each others parent and stopping the check in this situation. Fixes: b7eddd0b3950 ("batman-adv: prevent using any virtual device created on batman-adv as hard-interface") Signed-off-by: Andrew Lunn [sven@narfation.org: rewritten description, extracted fix] Signed-off-by: Sven Eckelmann Signed-off-by: Marek Lindner Signed-off-by: Antonio Quartulli --- net/batman-adv/hard-interface.c | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 01acccc4d218..57f7107169f5 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -75,6 +75,28 @@ out: return hard_iface; } +/** + * batadv_mutual_parents - check if two devices are each others parent + * @dev1: 1st net_device + * @dev2: 2nd net_device + * + * veth devices come in pairs and each is the parent of the other! + * + * Return: true if the devices are each others parent, otherwise false + */ +static bool batadv_mutual_parents(const struct net_device *dev1, + const struct net_device *dev2) +{ + int dev1_parent_iflink = dev_get_iflink(dev1); + int dev2_parent_iflink = dev_get_iflink(dev2); + + if (!dev1_parent_iflink || !dev2_parent_iflink) + return false; + + return (dev1_parent_iflink == dev2->ifindex) && + (dev2_parent_iflink == dev1->ifindex); +} + /** * batadv_is_on_batman_iface - check if a device is a batman iface descendant * @net_dev: the device to check @@ -108,6 +130,9 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev) if (WARN(!parent_dev, "Cannot find parent device")) return false; + if (batadv_mutual_parents(net_dev, parent_dev)) + return false; + ret = batadv_is_on_batman_iface(parent_dev); return ret; From 09ccbb74b6718ad4d1290de3f5669212c0ac7d4b Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 15 Feb 2016 19:41:45 +0100 Subject: [PATCH 179/489] drm/amdgpu: use post-decrement in error handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to use post-decrement to get the pci_map_page undone also for i==0, and to avoid some very unpleasant behaviour if pci_map_page failed already at i==0. Reviewed-by: Christian König Signed-off-by: Rasmus Villemoes Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c index 6442a06d6fdc..1cbb16e15307 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c @@ -712,7 +712,7 @@ static int amdgpu_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(adev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(adev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; From bc3f5d8c4ca01555820617eb3b6c0857e4df710d Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 15 Feb 2016 19:41:47 +0100 Subject: [PATCH 180/489] drm/radeon: use post-decrement in error handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We need to use post-decrement to get the pci_map_page undone also for i==0, and to avoid some very unpleasant behaviour if pci_map_page failed already at i==0. Reviewed-by: Christian König Signed-off-by: Rasmus Villemoes Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_ttm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c index e34307459e50..e06ac546a90f 100644 --- a/drivers/gpu/drm/radeon/radeon_ttm.c +++ b/drivers/gpu/drm/radeon/radeon_ttm.c @@ -758,7 +758,7 @@ static int radeon_ttm_tt_populate(struct ttm_tt *ttm) 0, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); if (pci_dma_mapping_error(rdev->pdev, gtt->ttm.dma_address[i])) { - while (--i) { + while (i--) { pci_unmap_page(rdev->pdev, gtt->ttm.dma_address[i], PAGE_SIZE, PCI_DMA_BIDIRECTIONAL); gtt->ttm.dma_address[i] = 0; From 1b92ee3d03af6643df395300ba7748f19ecdb0c5 Mon Sep 17 00:00:00 2001 From: Rainer Weikusat Date: Mon, 8 Feb 2016 18:47:19 +0000 Subject: [PATCH 181/489] af_unix: Don't set err in unix_stream_read_generic unless there was an error The present unix_stream_read_generic contains various code sequences of the form err = -EDISASTER; if () goto out; This has the unfortunate side effect of possibly causing the error code to bleed through to the final out: return copied ? : err; and then to be wrongly returned if no data was copied because the caller didn't supply a data buffer, as demonstrated by the program available at http://pad.lv/1540731 Change it such that err is only set if an error condition was detected. Fixes: 3822b5c2fc62 ("af_unix: Revert 'lock_interruptible' in stream receive code") Reported-by: Joseph Salisbury Signed-off-by: Rainer Weikusat Signed-off-by: David S. Miller --- net/unix/af_unix.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 29be035f9c65..df923caa8389 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2277,13 +2277,15 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) size_t size = state->size; unsigned int last_len; - err = -EINVAL; - if (sk->sk_state != TCP_ESTABLISHED) + if (unlikely(sk->sk_state != TCP_ESTABLISHED)) { + err = -EINVAL; goto out; + } - err = -EOPNOTSUPP; - if (flags & MSG_OOB) + if (unlikely(flags & MSG_OOB)) { + err = -EOPNOTSUPP; goto out; + } target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, noblock); @@ -2329,9 +2331,11 @@ again: goto unlock; unix_state_unlock(sk); - err = -EAGAIN; - if (!timeo) + if (!timeo) { + err = -EAGAIN; break; + } + mutex_unlock(&u->readlock); timeo = unix_stream_data_wait(sk, timeo, last, From a5527dda344fff0514b7989ef7a755729769daa1 Mon Sep 17 00:00:00 2001 From: Rainer Weikusat Date: Thu, 11 Feb 2016 19:37:27 +0000 Subject: [PATCH 182/489] af_unix: Guard against other == sk in unix_dgram_sendmsg The unix_dgram_sendmsg routine use the following test if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { to determine if sk and other are in an n:1 association (either established via connect or by using sendto to send messages to an unrelated socket identified by address). This isn't correct as the specified address could have been bound to the sending socket itself or because this socket could have been connected to itself by the time of the unix_peer_get but disconnected before the unix_state_lock(other). In both cases, the if-block would be entered despite other == sk which might either block the sender unintentionally or lead to trying to unlock the same spin lock twice for a non-blocking send. Add a other != sk check to guard against this. Fixes: 7d267278a9ec ("unix: avoid use-after-free in ep_remove_wait_queue") Reported-By: Philipp Hahn Signed-off-by: Rainer Weikusat Tested-by: Philipp Hahn Signed-off-by: David S. Miller --- net/unix/af_unix.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index df923caa8389..c51e2831f498 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1781,7 +1781,12 @@ restart_locked: goto out_unlock; } - if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + /* other == sk && unix_peer(other) != sk if + * - unix_peer(sk) == NULL, destination address bound to sk + * - unix_peer(sk) == sk by time of get but disconnected before lock + */ + if (other != sk && + unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo); From 5ff8eaac1636bf6deae86491f4818c4c69d1a9ac Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 16 Feb 2016 11:34:07 -0700 Subject: [PATCH 183/489] writeback: keep superblock pinned during cgroup writeback association switches If cgroup writeback is in use, an inode is associated with a cgroup for writeback. If the inode's main dirtier changes to another cgroup, the association gets updated asynchronously. Nothing was pinning the superblock while such switches are in progress and superblock could go away while async switching is pending or in progress leading to crashes like the following. kernel BUG at fs/jbd2/transaction.c:319! invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 1 PID: 29158 Comm: kworker/1:10 Not tainted 4.5.0-rc3 #51 Hardware name: Google Google, BIOS Google 01/01/2011 Workqueue: events inode_switch_wbs_work_fn task: ffff880213dbbd40 ti: ffff880209264000 task.ti: ffff880209264000 RIP: 0010:[] [] start_this_handle+0x382/0x3e0 RSP: 0018:ffff880209267c30 EFLAGS: 00010202 ... Call Trace: [] jbd2__journal_start+0xf4/0x190 [] __ext4_journal_start_sb+0x4e/0x70 [] ext4_evict_inode+0x12c/0x3d0 [] evict+0xbb/0x190 [] iput+0x130/0x190 [] inode_switch_wbs_work_fn+0x343/0x4c0 [] process_one_work+0x129/0x300 [] worker_thread+0x126/0x480 [] kthread+0xc4/0xe0 [] ret_from_fork+0x3f/0x70 Fix it by bumping s_active while cgroup association switching is in flight. Signed-off-by: Tejun Heo Reported-and-tested-by: Tahsin Erdogan Link: http://lkml.kernel.org/g/CAAeU0aNCq7LGODvVGRU-oU_o-6enii5ey0p1c26D1ZzYwkDc5A@mail.gmail.com Fixes: d10c80955265 ("writeback: implement foreign cgroup inode bdi_writeback switching") Cc: stable@vger.kernel.org #v4.5+ Signed-off-by: Jens Axboe --- fs/fs-writeback.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6915c950e6e8..1f76d8950a57 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -317,6 +317,7 @@ static void inode_switch_wbs_work_fn(struct work_struct *work) struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; + struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; @@ -423,6 +424,7 @@ skip_switch: wb_put(new_wb); iput(inode); + deactivate_super(sb); kfree(isw); } @@ -469,11 +471,14 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); + if (inode->i_state & (I_WB_SWITCH | I_FREEING) || - inode_to_wb(inode) == isw->new_wb) { - spin_unlock(&inode->i_lock); - goto out_free; - } + inode_to_wb(inode) == isw->new_wb) + goto out_unlock; + + if (!atomic_inc_not_zero(&inode->i_sb->s_active)) + goto out_unlock; + inode->i_state |= I_WB_SWITCH; spin_unlock(&inode->i_lock); @@ -489,6 +494,8 @@ static void inode_switch_wbs(struct inode *inode, int new_wb_id) call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; +out_unlock: + spin_unlock(&inode->i_lock); out_free: if (isw->new_wb) wb_put(isw->new_wb); From d0c5f45ae3ede897114dea204fbaaa4dd18fa9cb Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 6 Feb 2016 17:46:35 +0300 Subject: [PATCH 184/489] ravb: kill duplicate setting of CCC.CSEL When adding support for the R-Car gen3 gPTP active in configuration mode, the code setting the CCC.CSEL field was duplicated due to an oversight. For R-Car gen 2 it's just redundant and for R-Car gen3 the write at this time is probably ignored due to CCC.GAC bit being already set... Fixes: f5d7837f96e5 ("ravb: ptp: Add CONFIG mode support") Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index ac43ed914fcf..6ccef24dfd25 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1814,10 +1814,6 @@ static int ravb_probe(struct platform_device *pdev) CCC_OPC_CONFIG | CCC_GAC | CCC_CSEL_HPB, CCC); } - /* Set CSEL value */ - ravb_write(ndev, (ravb_read(ndev, CCC) & ~CCC_CSEL) | CCC_CSEL_HPB, - CCC); - /* Set GTI value */ error = ravb_set_gti(ndev); if (error) From 50bfd83830b89f9273672dcaedf3b765724fd023 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 6 Feb 2016 17:47:22 +0300 Subject: [PATCH 185/489] ravb: skip gPTP start/stop on R-Car gen3 When adding support for the R-Car gen3 gPTP active in configuration mode, some call sites of ravb_ptp_{init|stop}() were missed due to an oversight. Add checks for the R-Car gen2 SoCs around these... Fixes: f5d7837f96e5 ("ravb: ptp: Add CONFIG mode support") Signed-off-by: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/renesas/ravb_main.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 6ccef24dfd25..744d7806a9ee 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -1139,7 +1139,8 @@ static int ravb_set_ringparam(struct net_device *ndev, if (netif_running(ndev)) { netif_device_detach(ndev); /* Stop PTP Clock driver */ - ravb_ptp_stop(ndev); + if (priv->chip_id == RCAR_GEN2) + ravb_ptp_stop(ndev); /* Wait for DMA stopping */ error = ravb_stop_dma(ndev); if (error) { @@ -1170,7 +1171,8 @@ static int ravb_set_ringparam(struct net_device *ndev, ravb_emac_init(ndev); /* Initialise PTP Clock driver */ - ravb_ptp_init(ndev, priv->pdev); + if (priv->chip_id == RCAR_GEN2) + ravb_ptp_init(ndev, priv->pdev); netif_device_attach(ndev); } @@ -1298,7 +1300,8 @@ static void ravb_tx_timeout_work(struct work_struct *work) netif_tx_stop_all_queues(ndev); /* Stop PTP Clock driver */ - ravb_ptp_stop(ndev); + if (priv->chip_id == RCAR_GEN2) + ravb_ptp_stop(ndev); /* Wait for DMA stopping */ ravb_stop_dma(ndev); @@ -1311,7 +1314,8 @@ static void ravb_tx_timeout_work(struct work_struct *work) ravb_emac_init(ndev); /* Initialise PTP Clock driver */ - ravb_ptp_init(ndev, priv->pdev); + if (priv->chip_id == RCAR_GEN2) + ravb_ptp_init(ndev, priv->pdev); netif_tx_start_all_queues(ndev); } From 50d899808d33a5b0aa82be23e824119944042689 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 6 Feb 2016 12:58:48 -0800 Subject: [PATCH 186/489] net: phy: bcm7xxx: Fix shadow mode 2 disabling The clear and set masks in the call to phy_set_clr_bits() called from bcm7xxx_config_init() are inverted. We need to fix this by swapping the two arguments, that is, set 0 bits, but clear the shade mode 2 enable bit. Fixes: b560a58c45c66 ("net: phy: add Broadcom BCM7xxx internal PHY driver") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index bf241a3ec5e5..234a28502793 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -270,7 +270,7 @@ static int bcm7xxx_config_init(struct phy_device *phydev) phy_write(phydev, MII_BCM7XXX_100TX_FALSE_CAR, 0x7555); /* reset shadow mode 2 */ - ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, 0); + ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, 0, MII_BCM7XXX_SHD_MODE_2); if (ret < 0) return ret; From c6dd213abe40132f83e6ee569d70f3d60aa8b257 Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 6 Feb 2016 12:58:49 -0800 Subject: [PATCH 187/489] net: phy: bcm7xxx: Fix 40nm EPHY features The PHY entries for BCM7425/29/35 declare the 40nm Ethernet PHY as being 10/100/1000 capable, while this is just a 10/100 capable PHY device, fix that. Fixes: d068b02cfdfc2 ("net: phy: add BCM7425 and BCM7429 PHYs") Fixes: 9458ceab4917 ("net: phy: bcm7xxx: Add entry for BCM7435") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 234a28502793..524806dd0f6b 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -337,7 +337,7 @@ static struct phy_driver bcm7xxx_driver[] = { .phy_id = PHY_ID_BCM7425, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM7425", - .features = PHY_GBIT_FEATURES | + .features = PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause, .flags = PHY_IS_INTERNAL, .config_init = bcm7xxx_config_init, @@ -349,7 +349,7 @@ static struct phy_driver bcm7xxx_driver[] = { .phy_id = PHY_ID_BCM7429, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM7429", - .features = PHY_GBIT_FEATURES | + .features = PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause, .flags = PHY_IS_INTERNAL, .config_init = bcm7xxx_config_init, @@ -361,7 +361,7 @@ static struct phy_driver bcm7xxx_driver[] = { .phy_id = PHY_ID_BCM7435, .phy_id_mask = 0xfffffff0, .name = "Broadcom BCM7435", - .features = PHY_GBIT_FEATURES | + .features = PHY_BASIC_FEATURES | SUPPORTED_Pause | SUPPORTED_Asym_Pause, .flags = PHY_IS_INTERNAL, .config_init = bcm7xxx_config_init, From 258bf44364263cb6391f35ebaca3c2366655bded Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 6 Feb 2016 12:58:50 -0800 Subject: [PATCH 188/489] net: phy: bcm7xxx: Fix bcm7xxx_config_init() check Since we were wrongly advertising gigabit features for these 10/100 only Ethernet PHYs, bcm7xxx_config_init() which is supposed to apply workaround would have not run since the check would be true, now that we have fixed the PHY features, remove that check since it has no reasoning to be there anymore. Fixes: e18556ee3bd83 ("net: phy: bcm7xxx: do not use PHY_BRCM_100MBPS_WAR") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 524806dd0f6b..568768abe3ed 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -250,10 +250,6 @@ static int bcm7xxx_config_init(struct phy_device *phydev) phy_write(phydev, MII_BCM7XXX_AUX_MODE, MII_BCM7XX_64CLK_MDIO); phy_read(phydev, MII_BCM7XXX_AUX_MODE); - /* Workaround only required for 100Mbits/sec capable PHYs */ - if (phydev->supported & PHY_GBIT_FEATURES) - return 0; - /* set shadow mode 2 */ ret = phy_set_clr_bits(phydev, MII_BCM7XXX_TEST, MII_BCM7XXX_SHD_MODE_2, MII_BCM7XXX_SHD_MODE_2); From 815717d1473e0d5c3a31c350975325e07ed736fa Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Sat, 6 Feb 2016 12:58:51 -0800 Subject: [PATCH 189/489] net: phy: bcm7xxx: Remove wildcard entries Remove the two wildcard entries, they serve no purpose and will match way too many devices, some of them being covered by the driver in drivers/net/phy/broadcom.c. Remove the now unused bcm7xxx_dummy_config_init() function which would produce a warning. Fixes: b560a58c45c6 ("net: phy: add Broadcom BCM7xxx internal PHY driver") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/bcm7xxx.c | 31 ------------------------------- 1 file changed, 31 deletions(-) diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 568768abe3ed..db507e3bcab9 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -303,11 +303,6 @@ static int bcm7xxx_suspend(struct phy_device *phydev) return 0; } -static int bcm7xxx_dummy_config_init(struct phy_device *phydev) -{ - return 0; -} - #define BCM7XXX_28NM_GPHY(_oui, _name) \ { \ .phy_id = (_oui), \ @@ -365,30 +360,6 @@ static struct phy_driver bcm7xxx_driver[] = { .read_status = genphy_read_status, .suspend = bcm7xxx_suspend, .resume = bcm7xxx_config_init, -}, { - .phy_id = PHY_BCM_OUI_4, - .phy_id_mask = 0xffff0000, - .name = "Broadcom BCM7XXX 40nm", - .features = PHY_GBIT_FEATURES | - SUPPORTED_Pause | SUPPORTED_Asym_Pause, - .flags = PHY_IS_INTERNAL, - .config_init = bcm7xxx_config_init, - .config_aneg = genphy_config_aneg, - .read_status = genphy_read_status, - .suspend = bcm7xxx_suspend, - .resume = bcm7xxx_config_init, -}, { - .phy_id = PHY_BCM_OUI_5, - .phy_id_mask = 0xffffff00, - .name = "Broadcom BCM7XXX 65nm", - .features = PHY_BASIC_FEATURES | - SUPPORTED_Pause | SUPPORTED_Asym_Pause, - .flags = PHY_IS_INTERNAL, - .config_init = bcm7xxx_dummy_config_init, - .config_aneg = genphy_config_aneg, - .read_status = genphy_read_status, - .suspend = bcm7xxx_suspend, - .resume = bcm7xxx_config_init, } }; static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { @@ -400,8 +371,6 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = { { PHY_ID_BCM7439, 0xfffffff0, }, { PHY_ID_BCM7435, 0xfffffff0, }, { PHY_ID_BCM7445, 0xfffffff0, }, - { PHY_BCM_OUI_4, 0xffff0000 }, - { PHY_BCM_OUI_5, 0xffffff00 }, { } }; From bd59cfc51df7ddc88755a60a1293cee55f5d0a12 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sat, 6 Feb 2016 22:23:20 +0100 Subject: [PATCH 190/489] net: smc91x: propagate irq return code The smc91x driver doesn't honor the probe deferral mechanism when the interrupt source is not yet available, such as one provided by a gpio controller not probed. Fix this by propagating the platform_get_irq() error code as the probe return value. Signed-off-by: Robert Jarzmik Cc: Sergei Shtylyov Signed-off-by: David S. Miller --- drivers/net/ethernet/smsc/smc91x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 0e2fc1a844ab..db7db8ac4ca3 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2342,8 +2342,8 @@ static int smc_drv_probe(struct platform_device *pdev) } ndev->irq = platform_get_irq(pdev, 0); - if (ndev->irq <= 0) { - ret = -ENODEV; + if (ndev->irq < 0) { + ret = ndev->irq; goto out_release_io; } /* From a5a23ad52d1310976891c30471f4ee8d73f3cc9e Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 8 Feb 2016 15:33:42 +0100 Subject: [PATCH 191/489] net: am79c961a: avoid %? in inline assembly The am79c961a.c driver fails to build with clang because of an unusual inline assembly construct: drivers/net/ethernet/amd/am79c961a.c:53:7: error: invalid % escape in inline assembly string "str%?h %1, [%2] @ NET_RAP\n\t" The same change has been done a decade ago in arch/arm as of 6a39dd6222dd ("[ARM] 3759/2: Remove uses of %?"), but apparently some drivers were missed. Signed-off-by: Arnd Bergmann Acked-by: Russell King Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/am79c961a.c | 64 ++++++++++++++-------------- 1 file changed, 32 insertions(+), 32 deletions(-) diff --git a/drivers/net/ethernet/amd/am79c961a.c b/drivers/net/ethernet/amd/am79c961a.c index 87e727b921dc..fcdf5dda448f 100644 --- a/drivers/net/ethernet/amd/am79c961a.c +++ b/drivers/net/ethernet/amd/am79c961a.c @@ -50,8 +50,8 @@ static const char version[] = static void write_rreg(u_long base, u_int reg, u_int val) { asm volatile( - "str%?h %1, [%2] @ NET_RAP\n\t" - "str%?h %0, [%2, #-4] @ NET_RDP" + "strh %1, [%2] @ NET_RAP\n\t" + "strh %0, [%2, #-4] @ NET_RDP" : : "r" (val), "r" (reg), "r" (ISAIO_BASE + 0x0464)); } @@ -60,8 +60,8 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg) { unsigned short v; asm volatile( - "str%?h %1, [%2] @ NET_RAP\n\t" - "ldr%?h %0, [%2, #-4] @ NET_RDP" + "strh %1, [%2] @ NET_RAP\n\t" + "ldrh %0, [%2, #-4] @ NET_RDP" : "=r" (v) : "r" (reg), "r" (ISAIO_BASE + 0x0464)); return v; @@ -70,8 +70,8 @@ static inline unsigned short read_rreg(u_long base_addr, u_int reg) static inline void write_ireg(u_long base, u_int reg, u_int val) { asm volatile( - "str%?h %1, [%2] @ NET_RAP\n\t" - "str%?h %0, [%2, #8] @ NET_IDP" + "strh %1, [%2] @ NET_RAP\n\t" + "strh %0, [%2, #8] @ NET_IDP" : : "r" (val), "r" (reg), "r" (ISAIO_BASE + 0x0464)); } @@ -80,8 +80,8 @@ static inline unsigned short read_ireg(u_long base_addr, u_int reg) { u_short v; asm volatile( - "str%?h %1, [%2] @ NAT_RAP\n\t" - "ldr%?h %0, [%2, #8] @ NET_IDP\n\t" + "strh %1, [%2] @ NAT_RAP\n\t" + "ldrh %0, [%2, #8] @ NET_IDP\n\t" : "=r" (v) : "r" (reg), "r" (ISAIO_BASE + 0x0464)); return v; @@ -96,7 +96,7 @@ am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigne offset = ISAMEM_BASE + (offset << 1); length = (length + 1) & ~1; if ((int)buf & 2) { - asm volatile("str%?h %2, [%0], #4" + asm volatile("strh %2, [%0], #4" : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8))); buf += 2; length -= 2; @@ -104,20 +104,20 @@ am_writebuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigne while (length > 8) { register unsigned int tmp asm("r2"), tmp2 asm("r3"); asm volatile( - "ldm%?ia %0!, {%1, %2}" + "ldmia %0!, {%1, %2}" : "+r" (buf), "=&r" (tmp), "=&r" (tmp2)); length -= 8; asm volatile( - "str%?h %1, [%0], #4\n\t" - "mov%? %1, %1, lsr #16\n\t" - "str%?h %1, [%0], #4\n\t" - "str%?h %2, [%0], #4\n\t" - "mov%? %2, %2, lsr #16\n\t" - "str%?h %2, [%0], #4" + "strh %1, [%0], #4\n\t" + "mov %1, %1, lsr #16\n\t" + "strh %1, [%0], #4\n\t" + "strh %2, [%0], #4\n\t" + "mov %2, %2, lsr #16\n\t" + "strh %2, [%0], #4" : "+r" (offset), "=&r" (tmp), "=&r" (tmp2)); } while (length > 0) { - asm volatile("str%?h %2, [%0], #4" + asm volatile("strh %2, [%0], #4" : "=&r" (offset) : "0" (offset), "r" (buf[0] | (buf[1] << 8))); buf += 2; length -= 2; @@ -132,23 +132,23 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned if ((int)buf & 2) { unsigned int tmp; asm volatile( - "ldr%?h %2, [%0], #4\n\t" - "str%?b %2, [%1], #1\n\t" - "mov%? %2, %2, lsr #8\n\t" - "str%?b %2, [%1], #1" + "ldrh %2, [%0], #4\n\t" + "strb %2, [%1], #1\n\t" + "mov %2, %2, lsr #8\n\t" + "strb %2, [%1], #1" : "=&r" (offset), "=&r" (buf), "=r" (tmp): "0" (offset), "1" (buf)); length -= 2; } while (length > 8) { register unsigned int tmp asm("r2"), tmp2 asm("r3"), tmp3; asm volatile( - "ldr%?h %2, [%0], #4\n\t" - "ldr%?h %4, [%0], #4\n\t" - "ldr%?h %3, [%0], #4\n\t" - "orr%? %2, %2, %4, lsl #16\n\t" - "ldr%?h %4, [%0], #4\n\t" - "orr%? %3, %3, %4, lsl #16\n\t" - "stm%?ia %1!, {%2, %3}" + "ldrh %2, [%0], #4\n\t" + "ldrh %4, [%0], #4\n\t" + "ldrh %3, [%0], #4\n\t" + "orr %2, %2, %4, lsl #16\n\t" + "ldrh %4, [%0], #4\n\t" + "orr %3, %3, %4, lsl #16\n\t" + "stmia %1!, {%2, %3}" : "=&r" (offset), "=&r" (buf), "=r" (tmp), "=r" (tmp2), "=r" (tmp3) : "0" (offset), "1" (buf)); length -= 8; @@ -156,10 +156,10 @@ am_readbuffer(struct net_device *dev, u_int offset, unsigned char *buf, unsigned while (length > 0) { unsigned int tmp; asm volatile( - "ldr%?h %2, [%0], #4\n\t" - "str%?b %2, [%1], #1\n\t" - "mov%? %2, %2, lsr #8\n\t" - "str%?b %2, [%1], #1" + "ldrh %2, [%0], #4\n\t" + "strb %2, [%1], #1\n\t" + "mov %2, %2, lsr #8\n\t" + "strb %2, [%1], #1" : "=&r" (offset), "=&r" (buf), "=r" (tmp) : "0" (offset), "1" (buf)); length -= 2; } From 266b495f11d6706018f66250cb02a788ff2490d7 Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Mon, 8 Feb 2016 12:10:02 -0800 Subject: [PATCH 192/489] bonding: don't use stale speed and duplex information There is presently a race condition between the bonding periodic link monitor and the updating of a slave's speed and duplex. The former occurs on a periodic basis, and the latter in response to a driver's calling of netif_carrier_on. It is possible for the periodic monitor to run between the driver call of netif_carrier_on and the receipt of the NETDEV_CHANGE event that causes bonding to update the slave's speed and duplex. This manifests most notably as a report that a slave is up and "0 Mbps full duplex" after enslavement, but in principle could report an incorrect speed and duplex after any link up event if the device comes up with a different speed or duplex. This affects the 802.3ad aggregator selection, as the speed and duplex are selection criteria. This is fixed by updating the speed and duplex in the periodic monitor, prior to using that information. This was done historically in bonding, but the call to bond_update_speed_duplex was removed in commit 876254ae2758 ("bonding: don't call update_speed_duplex() under spinlocks"), as it might sleep under lock. Later, the locking was changed to only hold RTNL, and so after commit 876254ae2758 ("bonding: don't call update_speed_duplex() under spinlocks") this call is again safe. Tested-by: "Tantilov, Emil S" Cc: Veaceslav Falico Cc: dingtianhong Fixes: 876254ae2758 ("bonding: don't call update_speed_duplex() under spinlocks") Signed-off-by: Jay Vosburgh Acked-by: Ding Tianhong Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 65a4107749df..b7f1a9919033 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2129,6 +2129,7 @@ static void bond_miimon_commit(struct bonding *bond) continue; case BOND_LINK_UP: + bond_update_speed_duplex(slave); bond_set_slave_link_state(slave, BOND_LINK_UP, BOND_SLAVE_NOTIFY_NOW); slave->last_link_up = jiffies; From e001523666d0b07592abe1822b78ed0e5c2a34ab Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 25 Jan 2016 13:05:00 -0800 Subject: [PATCH 193/489] drm/vc4: Validate that WAIT_BO padding is cleared. This is ABI future-proofing if we ever want to extend the pad to mean something. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_gem.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 48ce30a6f4b5..cc89ffcfc6aa 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -746,6 +746,9 @@ vc4_wait_bo_ioctl(struct drm_device *dev, void *data, struct drm_gem_object *gem_obj; struct vc4_bo *bo; + if (args->pad != 0) + return -EINVAL; + gem_obj = drm_gem_object_lookup(dev, file_priv, args->handle); if (!gem_obj) { DRM_ERROR("Failed to look up GEM BO %d\n", args->handle); From 54aec44ab02b1fa216706671ae12d64af74443c5 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 25 Jan 2016 13:52:41 -0800 Subject: [PATCH 194/489] drm/vc4: Fix the clear color for the first tile rendered. Apparently in hardware (as opposed to simulation), the clear colors need to be uploaded before the render config, otherwise they won't take effect. Fixes igt's vc4_wait_bo/used-bo-* subtests. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_render_cl.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c index 8a2a312e2c1b..dea97f45e5af 100644 --- a/drivers/gpu/drm/vc4/vc4_render_cl.c +++ b/drivers/gpu/drm/vc4/vc4_render_cl.c @@ -321,15 +321,6 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec, list_add_tail(&to_vc4_bo(&setup->rcl->base)->unref_head, &exec->unref_list); - rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG); - rcl_u32(setup, - (setup->color_write ? (setup->color_write->paddr + - args->color_write.offset) : - 0)); - rcl_u16(setup, args->width); - rcl_u16(setup, args->height); - rcl_u16(setup, args->color_write.bits); - /* The tile buffer gets cleared when the previous tile is stored. If * the clear values changed between frames, then the tile buffer has * stale clear values in it, so we have to do a store in None mode (no @@ -349,6 +340,15 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec, rcl_u32(setup, 0); /* no address, since we're in None mode */ } + rcl_u8(setup, VC4_PACKET_TILE_RENDERING_MODE_CONFIG); + rcl_u32(setup, + (setup->color_write ? (setup->color_write->paddr + + args->color_write.offset) : + 0)); + rcl_u16(setup, args->width); + rcl_u16(setup, args->height); + rcl_u16(setup, args->color_write.bits); + for (y = min_y_tile; y <= max_y_tile; y++) { for (x = min_x_tile; x <= max_x_tile; x++) { bool first = (x == min_x_tile && y == min_y_tile); From 2c68f1fcfb9cfc10deff9bc59774aa331a6fabd2 Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 25 Jan 2016 14:13:12 -0800 Subject: [PATCH 195/489] drm/vc4: Return an ERR_PTR from BO creation instead of NULL. Fixes igt vc4_create_bo/create-bo-0 by returning -EINVAL from the ioctl instead of -ENOMEM. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_bo.c | 16 ++++++++-------- drivers/gpu/drm/vc4/vc4_gem.c | 4 ++-- drivers/gpu/drm/vc4/vc4_irq.c | 2 +- drivers/gpu/drm/vc4/vc4_render_cl.c | 4 ++-- drivers/gpu/drm/vc4/vc4_validate.c | 4 ++-- 5 files changed, 15 insertions(+), 15 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c index 18dfe3ec9a62..22278bcfc60e 100644 --- a/drivers/gpu/drm/vc4/vc4_bo.c +++ b/drivers/gpu/drm/vc4/vc4_bo.c @@ -215,7 +215,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size, struct drm_gem_cma_object *cma_obj; if (size == 0) - return NULL; + return ERR_PTR(-EINVAL); /* First, try to get a vc4_bo from the kernel BO cache. */ if (from_cache) { @@ -237,7 +237,7 @@ struct vc4_bo *vc4_bo_create(struct drm_device *dev, size_t unaligned_size, if (IS_ERR(cma_obj)) { DRM_ERROR("Failed to allocate from CMA:\n"); vc4_bo_stats_dump(vc4); - return NULL; + return ERR_PTR(-ENOMEM); } } @@ -259,8 +259,8 @@ int vc4_dumb_create(struct drm_file *file_priv, args->size = args->pitch * args->height; bo = vc4_bo_create(dev, args->size, false); - if (!bo) - return -ENOMEM; + if (IS_ERR(bo)) + return PTR_ERR(bo); ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); drm_gem_object_unreference_unlocked(&bo->base.base); @@ -443,8 +443,8 @@ int vc4_create_bo_ioctl(struct drm_device *dev, void *data, * get zeroed, and that might leak data between users. */ bo = vc4_bo_create(dev, args->size, false); - if (!bo) - return -ENOMEM; + if (IS_ERR(bo)) + return PTR_ERR(bo); ret = drm_gem_handle_create(file_priv, &bo->base.base, &args->handle); drm_gem_object_unreference_unlocked(&bo->base.base); @@ -496,8 +496,8 @@ vc4_create_shader_bo_ioctl(struct drm_device *dev, void *data, } bo = vc4_bo_create(dev, args->size, true); - if (!bo) - return -ENOMEM; + if (IS_ERR(bo)) + return PTR_ERR(bo); ret = copy_from_user(bo->base.vaddr, (void __user *)(uintptr_t)args->data, diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index cc89ffcfc6aa..3bf679d367a1 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -578,9 +578,9 @@ vc4_get_bcl(struct drm_device *dev, struct vc4_exec_info *exec) } bo = vc4_bo_create(dev, exec_size, true); - if (!bo) { + if (IS_ERR(bo)) { DRM_ERROR("Couldn't allocate BO for binning\n"); - ret = -ENOMEM; + ret = PTR_ERR(bo); goto fail; } exec->exec_bo = &bo->base; diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c index b68060e758db..78a21357fb2d 100644 --- a/drivers/gpu/drm/vc4/vc4_irq.c +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -57,7 +57,7 @@ vc4_overflow_mem_work(struct work_struct *work) struct vc4_bo *bo; bo = vc4_bo_create(dev, 256 * 1024, true); - if (!bo) { + if (IS_ERR(bo)) { DRM_ERROR("Couldn't allocate binner overflow mem\n"); return; } diff --git a/drivers/gpu/drm/vc4/vc4_render_cl.c b/drivers/gpu/drm/vc4/vc4_render_cl.c index dea97f45e5af..0f12418725e5 100644 --- a/drivers/gpu/drm/vc4/vc4_render_cl.c +++ b/drivers/gpu/drm/vc4/vc4_render_cl.c @@ -316,8 +316,8 @@ static int vc4_create_rcl_bo(struct drm_device *dev, struct vc4_exec_info *exec, size += xtiles * ytiles * loop_body_size; setup->rcl = &vc4_bo_create(dev, size, true)->base; - if (!setup->rcl) - return -ENOMEM; + if (IS_ERR(setup->rcl)) + return PTR_ERR(setup->rcl); list_add_tail(&to_vc4_bo(&setup->rcl->base)->unref_head, &exec->unref_list); diff --git a/drivers/gpu/drm/vc4/vc4_validate.c b/drivers/gpu/drm/vc4/vc4_validate.c index e26d9f6face3..24c2c746e8f3 100644 --- a/drivers/gpu/drm/vc4/vc4_validate.c +++ b/drivers/gpu/drm/vc4/vc4_validate.c @@ -401,8 +401,8 @@ validate_tile_binning_config(VALIDATE_ARGS) tile_bo = vc4_bo_create(dev, exec->tile_alloc_offset + tile_alloc_size, true); exec->tile_bo = &tile_bo->base; - if (!exec->tile_bo) - return -ENOMEM; + if (IS_ERR(exec->tile_bo)) + return PTR_ERR(exec->tile_bo); list_add_tail(&tile_bo->unref_head, &exec->unref_list); /* tile alloc address. */ From 13cf8909ead67e313ea203ee524b3cf4b09b3c9d Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 25 Jan 2016 14:32:41 -0800 Subject: [PATCH 196/489] drm/vc4: Fix -ERESTARTSYS error return from BO waits. This caused the wait ioctls to claim that waiting had completed when we actually got interrupted by a signal before it was done. Fixes broken rendering throttling that produced serious lag in X window dragging. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_gem.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 3bf679d367a1..15619dbf34ca 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -340,12 +340,10 @@ vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno, uint64_t timeout_ns, finish_wait(&vc4->job_wait_queue, &wait); trace_vc4_wait_for_seqno_end(dev, seqno); - if (ret && ret != -ERESTARTSYS) { + if (ret && ret != -ERESTARTSYS) DRM_ERROR("timeout waiting for render thread idle\n"); - return ret; - } - return 0; + return ret; } static void From 2ee94657e2bbd13b358060edc91b2b2fdef9038f Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 25 Jan 2016 14:33:50 -0800 Subject: [PATCH 197/489] drm/vc4: Drop error message on seqno wait timeouts. These ioctls end up getting exposed to fairly directly to GL users, and having normal user operations print DRM errors is obviously wrong. The message was originally to give us some idea of what happened when a hang occurred, but we have a DRM_INFO from reset for that. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_gem.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 15619dbf34ca..a9d020e7e891 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -340,9 +340,6 @@ vc4_wait_for_seqno(struct drm_device *dev, uint64_t seqno, uint64_t timeout_ns, finish_wait(&vc4->job_wait_queue, &wait); trace_vc4_wait_for_seqno_end(dev, seqno); - if (ret && ret != -ERESTARTSYS) - DRM_ERROR("timeout waiting for render thread idle\n"); - return ret; } From c4ce60dc30912df09b2438f1e5594eae1ef64d1e Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 8 Feb 2016 11:19:14 -0800 Subject: [PATCH 198/489] drm/vc4: Fix spurious GPU resets due to BO reuse. We were tracking the "where are the head pointers pointing" globally, so if another job reused the same BOs and execution was at the same point as last time we checked, we'd stop and trigger a reset even though the GPU had made progress. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_drv.h | 6 +++++- drivers/gpu/drm/vc4/vc4_gem.c | 19 ++++++++++++++----- 2 files changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 080865ec2bae..b6ccf8181643 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -92,7 +92,6 @@ struct vc4_dev { struct work_struct overflow_mem_work; struct { - uint32_t last_ct0ca, last_ct1ca; struct timer_list timer; struct work_struct reset_work; } hangcheck; @@ -192,6 +191,11 @@ struct vc4_exec_info { /* Sequence number for this bin/render job. */ uint64_t seqno; + /* Last current addresses the hardware was processing when the + * hangcheck timer checked on us. + */ + uint32_t last_ct0ca, last_ct1ca; + /* Kernel-space copy of the ioctl arguments */ struct drm_vc4_submit_cl *args; diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index a9d020e7e891..1a819dd826f8 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -257,10 +257,17 @@ vc4_hangcheck_elapsed(unsigned long data) struct drm_device *dev = (struct drm_device *)data; struct vc4_dev *vc4 = to_vc4_dev(dev); uint32_t ct0ca, ct1ca; + unsigned long irqflags; + struct vc4_exec_info *exec; + + spin_lock_irqsave(&vc4->job_lock, irqflags); + exec = vc4_first_job(vc4); /* If idle, we can stop watching for hangs. */ - if (list_empty(&vc4->job_list)) + if (!exec) { + spin_unlock_irqrestore(&vc4->job_lock, irqflags); return; + } ct0ca = V3D_READ(V3D_CTNCA(0)); ct1ca = V3D_READ(V3D_CTNCA(1)); @@ -268,14 +275,16 @@ vc4_hangcheck_elapsed(unsigned long data) /* If we've made any progress in execution, rearm the timer * and wait. */ - if (ct0ca != vc4->hangcheck.last_ct0ca || - ct1ca != vc4->hangcheck.last_ct1ca) { - vc4->hangcheck.last_ct0ca = ct0ca; - vc4->hangcheck.last_ct1ca = ct1ca; + if (ct0ca != exec->last_ct0ca || ct1ca != exec->last_ct1ca) { + exec->last_ct0ca = ct0ca; + exec->last_ct1ca = ct1ca; + spin_unlock_irqrestore(&vc4->job_lock, irqflags); vc4_queue_hangcheck(dev); return; } + spin_unlock_irqrestore(&vc4->job_lock, irqflags); + /* We've gone too long with no progress, reset. This has to * be done from a work struct, since resetting can sleep and * this timer hook isn't allowed to. From 001bdb55d9eb72a9e2d5b623bacfc52da74ae03e Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Fri, 5 Feb 2016 17:41:49 -0800 Subject: [PATCH 199/489] drm/vc4: Enable runtime PM. This may actually get us a feature that the closed driver didn't have: turning off the GPU in between rendering jobs, while the V3D device is still opened by the client. There may be some tuning to be applied here to use autosuspend so that we don't bounce the device's power so much, but in steady-state GPU-bound rendering we keep the power on (since we keep multiple jobs outstanding) and even if we power cycle on every job we can still manage at least 680 fps. More importantly, though, runtime PM will allow us to power off the device to do a GPU reset. v2: Switch #ifdef to CONFIG_PM not CONFIG_PM_SLEEP (caught by kbuild test robot) Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_drv.h | 1 + drivers/gpu/drm/vc4/vc4_gem.c | 10 ++++++++++ drivers/gpu/drm/vc4/vc4_v3d.c | 36 +++++++++++++++++++++++++++++++++++ 3 files changed, 47 insertions(+) diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index b6ccf8181643..8ac3788846ce 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -141,6 +141,7 @@ struct vc4_seqno_cb { }; struct vc4_v3d { + struct vc4_dev *vc4; struct platform_device *pdev; void __iomem *regs; }; diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 1a819dd826f8..4e0391cbf9d0 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -23,6 +23,7 @@ #include #include +#include #include #include @@ -621,6 +622,7 @@ fail: static void vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) { + struct vc4_dev *vc4 = to_vc4_dev(dev); unsigned i; /* Need the struct lock for drm_gem_object_unreference(). */ @@ -639,6 +641,8 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) } mutex_unlock(&dev->struct_mutex); + pm_runtime_put(&vc4->v3d->pdev->dev); + kfree(exec); } @@ -792,6 +796,12 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, return -ENOMEM; } + ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); + if (ret < 0) { + kfree(exec); + return ret; + } + exec->args = args; INIT_LIST_HEAD(&exec->unref_list); diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index 314ff71db978..cb38b6bf4119 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -17,6 +17,7 @@ */ #include "linux/component.h" +#include "linux/pm_runtime.h" #include "vc4_drv.h" #include "vc4_regs.h" @@ -167,6 +168,29 @@ static void vc4_v3d_init_hw(struct drm_device *dev) V3D_WRITE(V3D_VPMBASE, 0); } +#ifdef CONFIG_PM +static int vc4_v3d_runtime_suspend(struct device *dev) +{ + struct vc4_v3d *v3d = dev_get_drvdata(dev); + struct vc4_dev *vc4 = v3d->vc4; + + vc4_irq_uninstall(vc4->dev); + + return 0; +} + +static int vc4_v3d_runtime_resume(struct device *dev) +{ + struct vc4_v3d *v3d = dev_get_drvdata(dev); + struct vc4_dev *vc4 = v3d->vc4; + + vc4_v3d_init_hw(vc4->dev); + vc4_irq_postinstall(vc4->dev); + + return 0; +} +#endif + static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) { struct platform_device *pdev = to_platform_device(dev); @@ -179,6 +203,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) if (!v3d) return -ENOMEM; + dev_set_drvdata(dev, v3d); + v3d->pdev = pdev; v3d->regs = vc4_ioremap_regs(pdev, 0); @@ -186,6 +212,7 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) return PTR_ERR(v3d->regs); vc4->v3d = v3d; + v3d->vc4 = vc4; if (V3D_READ(V3D_IDENT0) != V3D_EXPECTED_IDENT0) { DRM_ERROR("V3D_IDENT0 read 0x%08x instead of 0x%08x\n", @@ -207,6 +234,8 @@ static int vc4_v3d_bind(struct device *dev, struct device *master, void *data) return ret; } + pm_runtime_enable(dev); + return 0; } @@ -216,6 +245,8 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master, struct drm_device *drm = dev_get_drvdata(master); struct vc4_dev *vc4 = to_vc4_dev(drm); + pm_runtime_disable(dev); + drm_irq_uninstall(drm); /* Disable the binner's overflow memory address, so the next @@ -228,6 +259,10 @@ static void vc4_v3d_unbind(struct device *dev, struct device *master, vc4->v3d = NULL; } +static const struct dev_pm_ops vc4_v3d_pm_ops = { + SET_RUNTIME_PM_OPS(vc4_v3d_runtime_suspend, vc4_v3d_runtime_resume, NULL) +}; + static const struct component_ops vc4_v3d_ops = { .bind = vc4_v3d_bind, .unbind = vc4_v3d_unbind, @@ -255,5 +290,6 @@ struct platform_driver vc4_v3d_driver = { .driver = { .name = "vc4_v3d", .of_match_table = vc4_v3d_dt_match, + .pm = &vc4_v3d_pm_ops, }, }; From 36cb6253f9383fd9a59ee7b8458c6232ef48577c Mon Sep 17 00:00:00 2001 From: Eric Anholt Date: Mon, 8 Feb 2016 12:59:02 -0800 Subject: [PATCH 200/489] drm/vc4: Use runtime PM to power cycle the device when the GPU hangs. This gets us functional GPU reset again, like we had until a refactor at merge time. Tested with a little patch to stuff in a broken binner job every 100 frames. Signed-off-by: Eric Anholt --- drivers/gpu/drm/vc4/vc4_drv.h | 6 +++++- drivers/gpu/drm/vc4/vc4_gem.c | 26 +++++++++++++++++++++----- drivers/gpu/drm/vc4/vc4_v3d.c | 12 ------------ 3 files changed, 26 insertions(+), 18 deletions(-) diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h index 8ac3788846ce..51a63330d4f8 100644 --- a/drivers/gpu/drm/vc4/vc4_drv.h +++ b/drivers/gpu/drm/vc4/vc4_drv.h @@ -91,6 +91,11 @@ struct vc4_dev { struct vc4_bo *overflow_mem; struct work_struct overflow_mem_work; + int power_refcount; + + /* Mutex controlling the power refcount. */ + struct mutex power_lock; + struct { struct timer_list timer; struct work_struct reset_work; @@ -439,7 +444,6 @@ void vc4_plane_async_set_fb(struct drm_plane *plane, extern struct platform_driver vc4_v3d_driver; int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused); int vc4_v3d_debugfs_regs(struct seq_file *m, void *unused); -int vc4_v3d_set_power(struct vc4_dev *vc4, bool on); /* vc4_validate.c */ int diff --git a/drivers/gpu/drm/vc4/vc4_gem.c b/drivers/gpu/drm/vc4/vc4_gem.c index 4e0391cbf9d0..202aa1544acc 100644 --- a/drivers/gpu/drm/vc4/vc4_gem.c +++ b/drivers/gpu/drm/vc4/vc4_gem.c @@ -229,8 +229,16 @@ vc4_reset(struct drm_device *dev) struct vc4_dev *vc4 = to_vc4_dev(dev); DRM_INFO("Resetting GPU.\n"); - vc4_v3d_set_power(vc4, false); - vc4_v3d_set_power(vc4, true); + + mutex_lock(&vc4->power_lock); + if (vc4->power_refcount) { + /* Power the device off and back on the by dropping the + * reference on runtime PM. + */ + pm_runtime_put_sync_suspend(&vc4->v3d->pdev->dev); + pm_runtime_get_sync(&vc4->v3d->pdev->dev); + } + mutex_unlock(&vc4->power_lock); vc4_irq_reset(dev); @@ -641,7 +649,10 @@ vc4_complete_exec(struct drm_device *dev, struct vc4_exec_info *exec) } mutex_unlock(&dev->struct_mutex); - pm_runtime_put(&vc4->v3d->pdev->dev); + mutex_lock(&vc4->power_lock); + if (--vc4->power_refcount == 0) + pm_runtime_put(&vc4->v3d->pdev->dev); + mutex_unlock(&vc4->power_lock); kfree(exec); } @@ -783,7 +794,7 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, struct vc4_dev *vc4 = to_vc4_dev(dev); struct drm_vc4_submit_cl *args = data; struct vc4_exec_info *exec; - int ret; + int ret = 0; if ((args->flags & ~VC4_SUBMIT_CL_USE_CLEAR_COLOR) != 0) { DRM_ERROR("Unknown flags: 0x%02x\n", args->flags); @@ -796,7 +807,10 @@ vc4_submit_cl_ioctl(struct drm_device *dev, void *data, return -ENOMEM; } - ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); + mutex_lock(&vc4->power_lock); + if (vc4->power_refcount++ == 0) + ret = pm_runtime_get_sync(&vc4->v3d->pdev->dev); + mutex_unlock(&vc4->power_lock); if (ret < 0) { kfree(exec); return ret; @@ -856,6 +870,8 @@ vc4_gem_init(struct drm_device *dev) (unsigned long)dev); INIT_WORK(&vc4->job_done_work, vc4_job_done_work); + + mutex_init(&vc4->power_lock); } void diff --git a/drivers/gpu/drm/vc4/vc4_v3d.c b/drivers/gpu/drm/vc4/vc4_v3d.c index cb38b6bf4119..31de5d17bc85 100644 --- a/drivers/gpu/drm/vc4/vc4_v3d.c +++ b/drivers/gpu/drm/vc4/vc4_v3d.c @@ -145,18 +145,6 @@ int vc4_v3d_debugfs_ident(struct seq_file *m, void *unused) } #endif /* CONFIG_DEBUG_FS */ -int -vc4_v3d_set_power(struct vc4_dev *vc4, bool on) -{ - /* XXX: This interface is needed for GPU reset, and the way to - * do it is to turn our power domain off and back on. We - * can't just reset from within the driver, because the reset - * bits are in the power domain's register area, and get set - * during the poweron process. - */ - return 0; -} - static void vc4_v3d_init_hw(struct drm_device *dev) { struct vc4_dev *vc4 = to_vc4_dev(dev); From b4ff3a36d3e409d365a09b6b783ff895063ff4ef Mon Sep 17 00:00:00 2001 From: Matan Barak Date: Tue, 9 Feb 2016 14:57:42 +0200 Subject: [PATCH 201/489] net/mlx5: Use offset based reserved field names in the IFC header file mlx5_ifc.h is a header file representing the API and ABI between the driver to the firmware and hardware. This file is used from both the mlx5_ib and mlx5_core drivers. Previously, this file used incrementing counter to indicate reserved fields, for example: struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 send[0x1]; u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; u8 reserved_0[0x1]; u8 srq_receive[0x1]; u8 reserved_1[0x1a]; }; If one developer implements through net-next feature A that uses reserved_0, they replace it with featureA and renames reserved_1 to reserved_0. In the same kernel cycle, a 2nd developer could implement feature B through the rdma tree, that uses reserved_1 and split it to featureB and a smaller reserved_1 field. This will cause a conflict when the two trees are merged. The source of this conflict is that the 1st developer changed *all* reserved fields. As Linus suggested, we change the layout of structs to: struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 send[0x1]; u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; u8 reserved_at_4[0x1]; u8 srq_receive[0x1]; u8 reserved_at_6[0x1a]; }; This makes the conflicts much more rare and preserves the locality of changes. Signed-off-by: Matan Barak Signed-off-by: Alaa Hleihel Reported-by: Linus Torvalds Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/mlx5/mlx5_ifc.h | 2968 ++++++++++++++++----------------- 1 file changed, 1484 insertions(+), 1484 deletions(-) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 231ab6bcea76..51f1e540fc2b 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -207,15 +207,15 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_dmac[0x1]; u8 outer_smac[0x1]; u8 outer_ether_type[0x1]; - u8 reserved_0[0x1]; + u8 reserved_at_3[0x1]; u8 outer_first_prio[0x1]; u8 outer_first_cfi[0x1]; u8 outer_first_vid[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_7[0x1]; u8 outer_second_prio[0x1]; u8 outer_second_cfi[0x1]; u8 outer_second_vid[0x1]; - u8 reserved_2[0x1]; + u8 reserved_at_b[0x1]; u8 outer_sip[0x1]; u8 outer_dip[0x1]; u8 outer_frag[0x1]; @@ -230,21 +230,21 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 outer_gre_protocol[0x1]; u8 outer_gre_key[0x1]; u8 outer_vxlan_vni[0x1]; - u8 reserved_3[0x5]; + u8 reserved_at_1a[0x5]; u8 source_eswitch_port[0x1]; u8 inner_dmac[0x1]; u8 inner_smac[0x1]; u8 inner_ether_type[0x1]; - u8 reserved_4[0x1]; + u8 reserved_at_23[0x1]; u8 inner_first_prio[0x1]; u8 inner_first_cfi[0x1]; u8 inner_first_vid[0x1]; - u8 reserved_5[0x1]; + u8 reserved_at_27[0x1]; u8 inner_second_prio[0x1]; u8 inner_second_cfi[0x1]; u8 inner_second_vid[0x1]; - u8 reserved_6[0x1]; + u8 reserved_at_2b[0x1]; u8 inner_sip[0x1]; u8 inner_dip[0x1]; u8 inner_frag[0x1]; @@ -256,37 +256,37 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 inner_tcp_sport[0x1]; u8 inner_tcp_dport[0x1]; u8 inner_tcp_flags[0x1]; - u8 reserved_7[0x9]; + u8 reserved_at_37[0x9]; - u8 reserved_8[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_flow_table_prop_layout_bits { u8 ft_support[0x1]; - u8 reserved_0[0x2]; + u8 reserved_at_1[0x2]; u8 flow_modify_en[0x1]; u8 modify_root[0x1]; u8 identified_miss_table_mode[0x1]; u8 flow_table_modify[0x1]; - u8 reserved_1[0x19]; + u8 reserved_at_7[0x19]; - u8 reserved_2[0x2]; + u8 reserved_at_20[0x2]; u8 log_max_ft_size[0x6]; - u8 reserved_3[0x10]; + u8 reserved_at_28[0x10]; u8 max_ft_level[0x8]; - u8 reserved_4[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_5[0x18]; + u8 reserved_at_60[0x18]; u8 log_max_ft_num[0x8]; - u8 reserved_6[0x18]; + u8 reserved_at_80[0x18]; u8 log_max_destination[0x8]; - u8 reserved_7[0x18]; + u8 reserved_at_a0[0x18]; u8 log_max_flow[0x8]; - u8 reserved_8[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_flow_table_fields_supported_bits ft_field_support; @@ -298,13 +298,13 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 receive[0x1]; u8 write[0x1]; u8 read[0x1]; - u8 reserved_0[0x1]; + u8 reserved_at_4[0x1]; u8 srq_receive[0x1]; - u8 reserved_1[0x1a]; + u8 reserved_at_6[0x1a]; }; struct mlx5_ifc_ipv4_layout_bits { - u8 reserved_0[0x60]; + u8 reserved_at_0[0x60]; u8 ipv4[0x20]; }; @@ -316,7 +316,7 @@ struct mlx5_ifc_ipv6_layout_bits { union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { struct mlx5_ifc_ipv6_layout_bits ipv6_layout; struct mlx5_ifc_ipv4_layout_bits ipv4_layout; - u8 reserved_0[0x80]; + u8 reserved_at_0[0x80]; }; struct mlx5_ifc_fte_match_set_lyr_2_4_bits { @@ -336,15 +336,15 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 ip_dscp[0x6]; u8 ip_ecn[0x2]; u8 vlan_tag[0x1]; - u8 reserved_0[0x1]; + u8 reserved_at_91[0x1]; u8 frag[0x1]; - u8 reserved_1[0x4]; + u8 reserved_at_93[0x4]; u8 tcp_flags[0x9]; u8 tcp_sport[0x10]; u8 tcp_dport[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_c0[0x20]; u8 udp_sport[0x10]; u8 udp_dport[0x10]; @@ -355,9 +355,9 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits { }; struct mlx5_ifc_fte_match_set_misc_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 source_port[0x10]; u8 outer_second_prio[0x3]; @@ -369,31 +369,31 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 outer_second_vlan_tag[0x1]; u8 inner_second_vlan_tag[0x1]; - u8 reserved_2[0xe]; + u8 reserved_at_62[0xe]; u8 gre_protocol[0x10]; u8 gre_key_h[0x18]; u8 gre_key_l[0x8]; u8 vxlan_vni[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_b8[0x8]; - u8 reserved_4[0x20]; + u8 reserved_at_c0[0x20]; - u8 reserved_5[0xc]; + u8 reserved_at_e0[0xc]; u8 outer_ipv6_flow_label[0x14]; - u8 reserved_6[0xc]; + u8 reserved_at_100[0xc]; u8 inner_ipv6_flow_label[0x14]; - u8 reserved_7[0xe0]; + u8 reserved_at_120[0xe0]; }; struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; u8 pa_l[0x14]; - u8 reserved_0[0xc]; + u8 reserved_at_34[0xc]; }; struct mlx5_ifc_uint64_bits { @@ -418,31 +418,31 @@ enum { struct mlx5_ifc_ads_bits { u8 fl[0x1]; u8 free_ar[0x1]; - u8 reserved_0[0xe]; + u8 reserved_at_2[0xe]; u8 pkey_index[0x10]; - u8 reserved_1[0x8]; + u8 reserved_at_20[0x8]; u8 grh[0x1]; u8 mlid[0x7]; u8 rlid[0x10]; u8 ack_timeout[0x5]; - u8 reserved_2[0x3]; + u8 reserved_at_45[0x3]; u8 src_addr_index[0x8]; - u8 reserved_3[0x4]; + u8 reserved_at_50[0x4]; u8 stat_rate[0x4]; u8 hop_limit[0x8]; - u8 reserved_4[0x4]; + u8 reserved_at_60[0x4]; u8 tclass[0x8]; u8 flow_label[0x14]; u8 rgid_rip[16][0x8]; - u8 reserved_5[0x4]; + u8 reserved_at_100[0x4]; u8 f_dscp[0x1]; u8 f_ecn[0x1]; - u8 reserved_6[0x1]; + u8 reserved_at_106[0x1]; u8 f_eth_prio[0x1]; u8 ecn[0x2]; u8 dscp[0x6]; @@ -458,25 +458,25 @@ struct mlx5_ifc_ads_bits { }; struct mlx5_ifc_flow_table_nic_cap_bits { - u8 reserved_0[0x200]; + u8 reserved_at_0[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive; - u8 reserved_1[0x200]; + u8 reserved_at_400[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_receive_sniffer; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit; - u8 reserved_2[0x200]; + u8 reserved_at_a00[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer; - u8 reserved_3[0x7200]; + u8 reserved_at_e00[0x7200]; }; struct mlx5_ifc_flow_table_eswitch_cap_bits { - u8 reserved_0[0x200]; + u8 reserved_at_0[0x200]; struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_esw_fdb; @@ -484,7 +484,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_esw_acl_egress; - u8 reserved_1[0x7800]; + u8 reserved_at_800[0x7800]; }; struct mlx5_ifc_e_switch_cap_bits { @@ -493,9 +493,9 @@ struct mlx5_ifc_e_switch_cap_bits { u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert_if_not_exist[0x1]; u8 vport_cvlan_insert_overwrite[0x1]; - u8 reserved_0[0x1b]; + u8 reserved_at_5[0x1b]; - u8 reserved_1[0x7e0]; + u8 reserved_at_20[0x7e0]; }; struct mlx5_ifc_per_protocol_networking_offload_caps_bits { @@ -504,51 +504,51 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits { u8 lro_cap[0x1]; u8 lro_psh_flag[0x1]; u8 lro_time_stamp[0x1]; - u8 reserved_0[0x3]; + u8 reserved_at_5[0x3]; u8 self_lb_en_modifiable[0x1]; - u8 reserved_1[0x2]; + u8 reserved_at_9[0x2]; u8 max_lso_cap[0x5]; - u8 reserved_2[0x4]; + u8 reserved_at_10[0x4]; u8 rss_ind_tbl_cap[0x4]; - u8 reserved_3[0x3]; + u8 reserved_at_18[0x3]; u8 tunnel_lso_const_out_ip_id[0x1]; - u8 reserved_4[0x2]; + u8 reserved_at_1c[0x2]; u8 tunnel_statless_gre[0x1]; u8 tunnel_stateless_vxlan[0x1]; - u8 reserved_5[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_6[0x10]; + u8 reserved_at_40[0x10]; u8 lro_min_mss_size[0x10]; - u8 reserved_7[0x120]; + u8 reserved_at_60[0x120]; u8 lro_timer_supported_periods[4][0x20]; - u8 reserved_8[0x600]; + u8 reserved_at_200[0x600]; }; struct mlx5_ifc_roce_cap_bits { u8 roce_apm[0x1]; - u8 reserved_0[0x1f]; + u8 reserved_at_1[0x1f]; - u8 reserved_1[0x60]; + u8 reserved_at_20[0x60]; - u8 reserved_2[0xc]; + u8 reserved_at_80[0xc]; u8 l3_type[0x4]; - u8 reserved_3[0x8]; + u8 reserved_at_90[0x8]; u8 roce_version[0x8]; - u8 reserved_4[0x10]; + u8 reserved_at_a0[0x10]; u8 r_roce_dest_udp_port[0x10]; u8 r_roce_max_src_udp_port[0x10]; u8 r_roce_min_src_udp_port[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_e0[0x10]; u8 roce_address_table_size[0x10]; - u8 reserved_6[0x700]; + u8 reserved_at_100[0x700]; }; enum { @@ -576,35 +576,35 @@ enum { }; struct mlx5_ifc_atomic_caps_bits { - u8 reserved_0[0x40]; + u8 reserved_at_0[0x40]; u8 atomic_req_8B_endianess_mode[0x2]; - u8 reserved_1[0x4]; + u8 reserved_at_42[0x4]; u8 supported_atomic_req_8B_endianess_mode_1[0x1]; - u8 reserved_2[0x19]; + u8 reserved_at_47[0x19]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; - u8 reserved_4[0x10]; + u8 reserved_at_80[0x10]; u8 atomic_operations[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_a0[0x10]; u8 atomic_size_qp[0x10]; - u8 reserved_6[0x10]; + u8 reserved_at_c0[0x10]; u8 atomic_size_dc[0x10]; - u8 reserved_7[0x720]; + u8 reserved_at_e0[0x720]; }; struct mlx5_ifc_odp_cap_bits { - u8 reserved_0[0x40]; + u8 reserved_at_0[0x40]; u8 sig[0x1]; - u8 reserved_1[0x1f]; + u8 reserved_at_41[0x1f]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_odp_per_transport_service_cap_bits rc_odp_caps; @@ -612,7 +612,7 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits ud_odp_caps; - u8 reserved_3[0x720]; + u8 reserved_at_e0[0x720]; }; enum { @@ -660,55 +660,55 @@ enum { }; struct mlx5_ifc_cmd_hca_cap_bits { - u8 reserved_0[0x80]; + u8 reserved_at_0[0x80]; u8 log_max_srq_sz[0x8]; u8 log_max_qp_sz[0x8]; - u8 reserved_1[0xb]; + u8 reserved_at_90[0xb]; u8 log_max_qp[0x5]; - u8 reserved_2[0xb]; + u8 reserved_at_a0[0xb]; u8 log_max_srq[0x5]; - u8 reserved_3[0x10]; + u8 reserved_at_b0[0x10]; - u8 reserved_4[0x8]; + u8 reserved_at_c0[0x8]; u8 log_max_cq_sz[0x8]; - u8 reserved_5[0xb]; + u8 reserved_at_d0[0xb]; u8 log_max_cq[0x5]; u8 log_max_eq_sz[0x8]; - u8 reserved_6[0x2]; + u8 reserved_at_e8[0x2]; u8 log_max_mkey[0x6]; - u8 reserved_7[0xc]; + u8 reserved_at_f0[0xc]; u8 log_max_eq[0x4]; u8 max_indirection[0x8]; - u8 reserved_8[0x1]; + u8 reserved_at_108[0x1]; u8 log_max_mrw_sz[0x7]; - u8 reserved_9[0x2]; + u8 reserved_at_110[0x2]; u8 log_max_bsf_list_size[0x6]; - u8 reserved_10[0x2]; + u8 reserved_at_118[0x2]; u8 log_max_klm_list_size[0x6]; - u8 reserved_11[0xa]; + u8 reserved_at_120[0xa]; u8 log_max_ra_req_dc[0x6]; - u8 reserved_12[0xa]; + u8 reserved_at_130[0xa]; u8 log_max_ra_res_dc[0x6]; - u8 reserved_13[0xa]; + u8 reserved_at_140[0xa]; u8 log_max_ra_req_qp[0x6]; - u8 reserved_14[0xa]; + u8 reserved_at_150[0xa]; u8 log_max_ra_res_qp[0x6]; u8 pad_cap[0x1]; u8 cc_query_allowed[0x1]; u8 cc_modify_allowed[0x1]; - u8 reserved_15[0xd]; + u8 reserved_at_163[0xd]; u8 gid_table_size[0x10]; u8 out_of_seq_cnt[0x1]; u8 vport_counters[0x1]; - u8 reserved_16[0x4]; + u8 reserved_at_182[0x4]; u8 max_qp_cnt[0xa]; u8 pkey_table_size[0x10]; @@ -716,158 +716,158 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 vhca_group_manager[0x1]; u8 ib_virt[0x1]; u8 eth_virt[0x1]; - u8 reserved_17[0x1]; + u8 reserved_at_1a4[0x1]; u8 ets[0x1]; u8 nic_flow_table[0x1]; u8 eswitch_flow_table[0x1]; u8 early_vf_enable; - u8 reserved_18[0x2]; + u8 reserved_at_1a8[0x2]; u8 local_ca_ack_delay[0x5]; - u8 reserved_19[0x6]; + u8 reserved_at_1af[0x6]; u8 port_type[0x2]; u8 num_ports[0x8]; - u8 reserved_20[0x3]; + u8 reserved_at_1bf[0x3]; u8 log_max_msg[0x5]; - u8 reserved_21[0x18]; + u8 reserved_at_1c7[0x18]; u8 stat_rate_support[0x10]; - u8 reserved_22[0xc]; + u8 reserved_at_1ef[0xc]; u8 cqe_version[0x4]; u8 compact_address_vector[0x1]; - u8 reserved_23[0xe]; + u8 reserved_at_200[0xe]; u8 drain_sigerr[0x1]; u8 cmdif_checksum[0x2]; u8 sigerr_cqe[0x1]; - u8 reserved_24[0x1]; + u8 reserved_at_212[0x1]; u8 wq_signature[0x1]; u8 sctr_data_cqe[0x1]; - u8 reserved_25[0x1]; + u8 reserved_at_215[0x1]; u8 sho[0x1]; u8 tph[0x1]; u8 rf[0x1]; u8 dct[0x1]; - u8 reserved_26[0x1]; + u8 reserved_at_21a[0x1]; u8 eth_net_offloads[0x1]; u8 roce[0x1]; u8 atomic[0x1]; - u8 reserved_27[0x1]; + u8 reserved_at_21e[0x1]; u8 cq_oi[0x1]; u8 cq_resize[0x1]; u8 cq_moderation[0x1]; - u8 reserved_28[0x3]; + u8 reserved_at_222[0x3]; u8 cq_eq_remap[0x1]; u8 pg[0x1]; u8 block_lb_mc[0x1]; - u8 reserved_29[0x1]; + u8 reserved_at_228[0x1]; u8 scqe_break_moderation[0x1]; - u8 reserved_30[0x1]; + u8 reserved_at_22a[0x1]; u8 cd[0x1]; - u8 reserved_31[0x1]; + u8 reserved_at_22c[0x1]; u8 apm[0x1]; - u8 reserved_32[0x7]; + u8 reserved_at_22e[0x7]; u8 qkv[0x1]; u8 pkv[0x1]; - u8 reserved_33[0x4]; + u8 reserved_at_237[0x4]; u8 xrc[0x1]; u8 ud[0x1]; u8 uc[0x1]; u8 rc[0x1]; - u8 reserved_34[0xa]; + u8 reserved_at_23f[0xa]; u8 uar_sz[0x6]; - u8 reserved_35[0x8]; + u8 reserved_at_24f[0x8]; u8 log_pg_sz[0x8]; u8 bf[0x1]; - u8 reserved_36[0x1]; + u8 reserved_at_260[0x1]; u8 pad_tx_eth_packet[0x1]; - u8 reserved_37[0x8]; + u8 reserved_at_262[0x8]; u8 log_bf_reg_size[0x5]; - u8 reserved_38[0x10]; + u8 reserved_at_26f[0x10]; - u8 reserved_39[0x10]; + u8 reserved_at_27f[0x10]; u8 max_wqe_sz_sq[0x10]; - u8 reserved_40[0x10]; + u8 reserved_at_29f[0x10]; u8 max_wqe_sz_rq[0x10]; - u8 reserved_41[0x10]; + u8 reserved_at_2bf[0x10]; u8 max_wqe_sz_sq_dc[0x10]; - u8 reserved_42[0x7]; + u8 reserved_at_2df[0x7]; u8 max_qp_mcg[0x19]; - u8 reserved_43[0x18]; + u8 reserved_at_2ff[0x18]; u8 log_max_mcg[0x8]; - u8 reserved_44[0x3]; + u8 reserved_at_31f[0x3]; u8 log_max_transport_domain[0x5]; - u8 reserved_45[0x3]; + u8 reserved_at_327[0x3]; u8 log_max_pd[0x5]; - u8 reserved_46[0xb]; + u8 reserved_at_32f[0xb]; u8 log_max_xrcd[0x5]; - u8 reserved_47[0x20]; + u8 reserved_at_33f[0x20]; - u8 reserved_48[0x3]; + u8 reserved_at_35f[0x3]; u8 log_max_rq[0x5]; - u8 reserved_49[0x3]; + u8 reserved_at_367[0x3]; u8 log_max_sq[0x5]; - u8 reserved_50[0x3]; + u8 reserved_at_36f[0x3]; u8 log_max_tir[0x5]; - u8 reserved_51[0x3]; + u8 reserved_at_377[0x3]; u8 log_max_tis[0x5]; u8 basic_cyclic_rcv_wqe[0x1]; - u8 reserved_52[0x2]; + u8 reserved_at_380[0x2]; u8 log_max_rmp[0x5]; - u8 reserved_53[0x3]; + u8 reserved_at_387[0x3]; u8 log_max_rqt[0x5]; - u8 reserved_54[0x3]; + u8 reserved_at_38f[0x3]; u8 log_max_rqt_size[0x5]; - u8 reserved_55[0x3]; + u8 reserved_at_397[0x3]; u8 log_max_tis_per_sq[0x5]; - u8 reserved_56[0x3]; + u8 reserved_at_39f[0x3]; u8 log_max_stride_sz_rq[0x5]; - u8 reserved_57[0x3]; + u8 reserved_at_3a7[0x3]; u8 log_min_stride_sz_rq[0x5]; - u8 reserved_58[0x3]; + u8 reserved_at_3af[0x3]; u8 log_max_stride_sz_sq[0x5]; - u8 reserved_59[0x3]; + u8 reserved_at_3b7[0x3]; u8 log_min_stride_sz_sq[0x5]; - u8 reserved_60[0x1b]; + u8 reserved_at_3bf[0x1b]; u8 log_max_wq_sz[0x5]; u8 nic_vport_change_event[0x1]; - u8 reserved_61[0xa]; + u8 reserved_at_3e0[0xa]; u8 log_max_vlan_list[0x5]; - u8 reserved_62[0x3]; + u8 reserved_at_3ef[0x3]; u8 log_max_current_mc_list[0x5]; - u8 reserved_63[0x3]; + u8 reserved_at_3f7[0x3]; u8 log_max_current_uc_list[0x5]; - u8 reserved_64[0x80]; + u8 reserved_at_3ff[0x80]; - u8 reserved_65[0x3]; + u8 reserved_at_47f[0x3]; u8 log_max_l2_table[0x5]; - u8 reserved_66[0x8]; + u8 reserved_at_487[0x8]; u8 log_uar_page_sz[0x10]; - u8 reserved_67[0x20]; + u8 reserved_at_49f[0x20]; u8 device_frequency_mhz[0x20]; u8 device_frequency_khz[0x20]; - u8 reserved_68[0x5f]; + u8 reserved_at_4ff[0x5f]; u8 cqe_zip[0x1]; u8 cqe_zip_timeout[0x10]; u8 cqe_zip_max_num[0x10]; - u8 reserved_69[0x220]; + u8 reserved_at_57f[0x220]; }; enum mlx5_flow_destination_type { @@ -880,7 +880,7 @@ struct mlx5_ifc_dest_format_struct_bits { u8 destination_type[0x8]; u8 destination_id[0x18]; - u8 reserved_0[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_fte_match_param_bits { @@ -890,7 +890,7 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_lyr_2_4_bits inner_headers; - u8 reserved_0[0xa00]; + u8 reserved_at_600[0xa00]; }; enum { @@ -922,18 +922,18 @@ struct mlx5_ifc_wq_bits { u8 wq_signature[0x1]; u8 end_padding_mode[0x2]; u8 cd_slave[0x1]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 hds_skip_first_sge[0x1]; u8 log2_hds_buf_size[0x3]; - u8 reserved_1[0x7]; + u8 reserved_at_24[0x7]; u8 page_offset[0x5]; u8 lwm[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 pd[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_60[0x8]; u8 uar_page[0x18]; u8 dbr_addr[0x40]; @@ -942,60 +942,60 @@ struct mlx5_ifc_wq_bits { u8 sw_counter[0x20]; - u8 reserved_4[0xc]; + u8 reserved_at_100[0xc]; u8 log_wq_stride[0x4]; - u8 reserved_5[0x3]; + u8 reserved_at_110[0x3]; u8 log_wq_pg_sz[0x5]; - u8 reserved_6[0x3]; + u8 reserved_at_118[0x3]; u8 log_wq_sz[0x5]; - u8 reserved_7[0x4e0]; + u8 reserved_at_120[0x4e0]; struct mlx5_ifc_cmd_pas_bits pas[0]; }; struct mlx5_ifc_rq_num_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 rq_num[0x18]; }; struct mlx5_ifc_mac_address_layout_bits { - u8 reserved_0[0x10]; + u8 reserved_at_0[0x10]; u8 mac_addr_47_32[0x10]; u8 mac_addr_31_0[0x20]; }; struct mlx5_ifc_vlan_layout_bits { - u8 reserved_0[0x14]; + u8 reserved_at_0[0x14]; u8 vlan[0x0c]; - u8 reserved_1[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_cong_control_r_roce_ecn_np_bits { - u8 reserved_0[0xa0]; + u8 reserved_at_0[0xa0]; u8 min_time_between_cnps[0x20]; - u8 reserved_1[0x12]; + u8 reserved_at_c0[0x12]; u8 cnp_dscp[0x6]; - u8 reserved_2[0x5]; + u8 reserved_at_d8[0x5]; u8 cnp_802p_prio[0x3]; - u8 reserved_3[0x720]; + u8 reserved_at_e0[0x720]; }; struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { - u8 reserved_0[0x60]; + u8 reserved_at_0[0x60]; - u8 reserved_1[0x4]; + u8 reserved_at_60[0x4]; u8 clamp_tgt_rate[0x1]; - u8 reserved_2[0x3]; + u8 reserved_at_65[0x3]; u8 clamp_tgt_rate_after_time_inc[0x1]; - u8 reserved_3[0x17]; + u8 reserved_at_69[0x17]; - u8 reserved_4[0x20]; + u8 reserved_at_80[0x20]; u8 rpg_time_reset[0x20]; @@ -1015,7 +1015,7 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { u8 rpg_min_rate[0x20]; - u8 reserved_5[0xe0]; + u8 reserved_at_1c0[0xe0]; u8 rate_to_set_on_first_cnp[0x20]; @@ -1025,15 +1025,15 @@ struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits { u8 rate_reduce_monitor_period[0x20]; - u8 reserved_6[0x20]; + u8 reserved_at_320[0x20]; u8 initial_alpha_value[0x20]; - u8 reserved_7[0x4a0]; + u8 reserved_at_360[0x4a0]; }; struct mlx5_ifc_cong_control_802_1qau_rp_bits { - u8 reserved_0[0x80]; + u8 reserved_at_0[0x80]; u8 rppp_max_rps[0x20]; @@ -1055,7 +1055,7 @@ struct mlx5_ifc_cong_control_802_1qau_rp_bits { u8 rpg_min_rate[0x20]; - u8 reserved_1[0x640]; + u8 reserved_at_1c0[0x640]; }; enum { @@ -1205,7 +1205,7 @@ struct mlx5_ifc_phys_layer_cntrs_bits { u8 successful_recovery_events[0x20]; - u8 reserved_0[0x180]; + u8 reserved_at_640[0x180]; }; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { @@ -1213,7 +1213,7 @@ struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits { u8 transmit_queue_low[0x20]; - u8 reserved_0[0x780]; + u8 reserved_at_40[0x780]; }; struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { @@ -1221,7 +1221,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 rx_octets_low[0x20]; - u8 reserved_0[0xc0]; + u8 reserved_at_40[0xc0]; u8 rx_frames_high[0x20]; @@ -1231,7 +1231,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 tx_octets_low[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_180[0xc0]; u8 tx_frames_high[0x20]; @@ -1257,7 +1257,7 @@ struct mlx5_ifc_eth_per_prio_grp_data_layout_bits { u8 rx_pause_transition_low[0x20]; - u8 reserved_2[0x400]; + u8 reserved_at_3c0[0x400]; }; struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { @@ -1265,7 +1265,7 @@ struct mlx5_ifc_eth_extended_cntrs_grp_data_layout_bits { u8 port_transmit_wait_low[0x20]; - u8 reserved_0[0x780]; + u8 reserved_at_40[0x780]; }; struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { @@ -1333,7 +1333,7 @@ struct mlx5_ifc_eth_3635_cntrs_grp_data_layout_bits { u8 dot3out_pause_frames_low[0x20]; - u8 reserved_0[0x3c0]; + u8 reserved_at_400[0x3c0]; }; struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { @@ -1421,7 +1421,7 @@ struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits { u8 ether_stats_pkts8192to10239octets_low[0x20]; - u8 reserved_0[0x280]; + u8 reserved_at_540[0x280]; }; struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { @@ -1477,7 +1477,7 @@ struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits { u8 if_out_broadcast_pkts_low[0x20]; - u8 reserved_0[0x480]; + u8 reserved_at_340[0x480]; }; struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { @@ -1557,54 +1557,54 @@ struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits { u8 a_pause_mac_ctrl_frames_transmitted_low[0x20]; - u8 reserved_0[0x300]; + u8 reserved_at_4c0[0x300]; }; struct mlx5_ifc_cmd_inter_comp_event_bits { u8 command_completion_vector[0x20]; - u8 reserved_0[0xc0]; + u8 reserved_at_20[0xc0]; }; struct mlx5_ifc_stall_vl_event_bits { - u8 reserved_0[0x18]; + u8 reserved_at_0[0x18]; u8 port_num[0x1]; - u8 reserved_1[0x3]; + u8 reserved_at_19[0x3]; u8 vl[0x4]; - u8 reserved_2[0xa0]; + u8 reserved_at_20[0xa0]; }; struct mlx5_ifc_db_bf_congestion_event_bits { u8 event_subtype[0x8]; - u8 reserved_0[0x8]; + u8 reserved_at_8[0x8]; u8 congestion_level[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_2[0xa0]; + u8 reserved_at_20[0xa0]; }; struct mlx5_ifc_gpio_event_bits { - u8 reserved_0[0x60]; + u8 reserved_at_0[0x60]; u8 gpio_event_hi[0x20]; u8 gpio_event_lo[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_a0[0x40]; }; struct mlx5_ifc_port_state_change_event_bits { - u8 reserved_0[0x40]; + u8 reserved_at_0[0x40]; u8 port_num[0x4]; - u8 reserved_1[0x1c]; + u8 reserved_at_44[0x1c]; - u8 reserved_2[0x80]; + u8 reserved_at_60[0x80]; }; struct mlx5_ifc_dropped_packet_logged_bits { - u8 reserved_0[0xe0]; + u8 reserved_at_0[0xe0]; }; enum { @@ -1613,15 +1613,15 @@ enum { }; struct mlx5_ifc_cq_error_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 cqn[0x18]; - u8 reserved_1[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 syndrome[0x8]; - u8 reserved_3[0x80]; + u8 reserved_at_60[0x80]; }; struct mlx5_ifc_rdma_page_fault_event_bits { @@ -1629,14 +1629,14 @@ struct mlx5_ifc_rdma_page_fault_event_bits { u8 r_key[0x20]; - u8 reserved_0[0x10]; + u8 reserved_at_40[0x10]; u8 packet_len[0x10]; u8 rdma_op_len[0x20]; u8 rdma_va[0x40]; - u8 reserved_1[0x5]; + u8 reserved_at_c0[0x5]; u8 rdma[0x1]; u8 write[0x1]; u8 requestor[0x1]; @@ -1646,15 +1646,15 @@ struct mlx5_ifc_rdma_page_fault_event_bits { struct mlx5_ifc_wqe_associated_page_fault_event_bits { u8 bytes_committed[0x20]; - u8 reserved_0[0x10]; + u8 reserved_at_20[0x10]; u8 wqe_index[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_40[0x10]; u8 len[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_60[0x60]; - u8 reserved_3[0x5]; + u8 reserved_at_c0[0x5]; u8 rdma[0x1]; u8 write_read[0x1]; u8 requestor[0x1]; @@ -1662,26 +1662,26 @@ struct mlx5_ifc_wqe_associated_page_fault_event_bits { }; struct mlx5_ifc_qp_events_bits { - u8 reserved_0[0xa0]; + u8 reserved_at_0[0xa0]; u8 type[0x8]; - u8 reserved_1[0x18]; + u8 reserved_at_a8[0x18]; - u8 reserved_2[0x8]; + u8 reserved_at_c0[0x8]; u8 qpn_rqn_sqn[0x18]; }; struct mlx5_ifc_dct_events_bits { - u8 reserved_0[0xc0]; + u8 reserved_at_0[0xc0]; - u8 reserved_1[0x8]; + u8 reserved_at_c0[0x8]; u8 dct_number[0x18]; }; struct mlx5_ifc_comp_event_bits { - u8 reserved_0[0xc0]; + u8 reserved_at_0[0xc0]; - u8 reserved_1[0x8]; + u8 reserved_at_c0[0x8]; u8 cq_number[0x18]; }; @@ -1754,41 +1754,41 @@ enum { struct mlx5_ifc_qpc_bits { u8 state[0x4]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 st[0x8]; - u8 reserved_1[0x3]; + u8 reserved_at_10[0x3]; u8 pm_state[0x2]; - u8 reserved_2[0x7]; + u8 reserved_at_15[0x7]; u8 end_padding_mode[0x2]; - u8 reserved_3[0x2]; + u8 reserved_at_1e[0x2]; u8 wq_signature[0x1]; u8 block_lb_mc[0x1]; u8 atomic_like_write_en[0x1]; u8 latency_sensitive[0x1]; - u8 reserved_4[0x1]; + u8 reserved_at_24[0x1]; u8 drain_sigerr[0x1]; - u8 reserved_5[0x2]; + u8 reserved_at_26[0x2]; u8 pd[0x18]; u8 mtu[0x3]; u8 log_msg_max[0x5]; - u8 reserved_6[0x1]; + u8 reserved_at_48[0x1]; u8 log_rq_size[0x4]; u8 log_rq_stride[0x3]; u8 no_sq[0x1]; u8 log_sq_size[0x4]; - u8 reserved_7[0x6]; + u8 reserved_at_55[0x6]; u8 rlky[0x1]; - u8 reserved_8[0x4]; + u8 reserved_at_5c[0x4]; u8 counter_set_id[0x8]; u8 uar_page[0x18]; - u8 reserved_9[0x8]; + u8 reserved_at_80[0x8]; u8 user_index[0x18]; - u8 reserved_10[0x3]; + u8 reserved_at_a0[0x3]; u8 log_page_size[0x5]; u8 remote_qpn[0x18]; @@ -1797,66 +1797,66 @@ struct mlx5_ifc_qpc_bits { struct mlx5_ifc_ads_bits secondary_address_path; u8 log_ack_req_freq[0x4]; - u8 reserved_11[0x4]; + u8 reserved_at_384[0x4]; u8 log_sra_max[0x3]; - u8 reserved_12[0x2]; + u8 reserved_at_38b[0x2]; u8 retry_count[0x3]; u8 rnr_retry[0x3]; - u8 reserved_13[0x1]; + u8 reserved_at_393[0x1]; u8 fre[0x1]; u8 cur_rnr_retry[0x3]; u8 cur_retry_count[0x3]; - u8 reserved_14[0x5]; + u8 reserved_at_39b[0x5]; - u8 reserved_15[0x20]; + u8 reserved_at_3a0[0x20]; - u8 reserved_16[0x8]; + u8 reserved_at_3c0[0x8]; u8 next_send_psn[0x18]; - u8 reserved_17[0x8]; + u8 reserved_at_3e0[0x8]; u8 cqn_snd[0x18]; - u8 reserved_18[0x40]; + u8 reserved_at_400[0x40]; - u8 reserved_19[0x8]; + u8 reserved_at_440[0x8]; u8 last_acked_psn[0x18]; - u8 reserved_20[0x8]; + u8 reserved_at_460[0x8]; u8 ssn[0x18]; - u8 reserved_21[0x8]; + u8 reserved_at_480[0x8]; u8 log_rra_max[0x3]; - u8 reserved_22[0x1]; + u8 reserved_at_48b[0x1]; u8 atomic_mode[0x4]; u8 rre[0x1]; u8 rwe[0x1]; u8 rae[0x1]; - u8 reserved_23[0x1]; + u8 reserved_at_493[0x1]; u8 page_offset[0x6]; - u8 reserved_24[0x3]; + u8 reserved_at_49a[0x3]; u8 cd_slave_receive[0x1]; u8 cd_slave_send[0x1]; u8 cd_master[0x1]; - u8 reserved_25[0x3]; + u8 reserved_at_4a0[0x3]; u8 min_rnr_nak[0x5]; u8 next_rcv_psn[0x18]; - u8 reserved_26[0x8]; + u8 reserved_at_4c0[0x8]; u8 xrcd[0x18]; - u8 reserved_27[0x8]; + u8 reserved_at_4e0[0x8]; u8 cqn_rcv[0x18]; u8 dbr_addr[0x40]; u8 q_key[0x20]; - u8 reserved_28[0x5]; + u8 reserved_at_560[0x5]; u8 rq_type[0x3]; u8 srqn_rmpn[0x18]; - u8 reserved_29[0x8]; + u8 reserved_at_580[0x8]; u8 rmsn[0x18]; u8 hw_sq_wqebb_counter[0x10]; @@ -1866,33 +1866,33 @@ struct mlx5_ifc_qpc_bits { u8 sw_rq_counter[0x20]; - u8 reserved_30[0x20]; + u8 reserved_at_600[0x20]; - u8 reserved_31[0xf]; + u8 reserved_at_620[0xf]; u8 cgs[0x1]; u8 cs_req[0x8]; u8 cs_res[0x8]; u8 dc_access_key[0x40]; - u8 reserved_32[0xc0]; + u8 reserved_at_680[0xc0]; }; struct mlx5_ifc_roce_addr_layout_bits { u8 source_l3_address[16][0x8]; - u8 reserved_0[0x3]; + u8 reserved_at_80[0x3]; u8 vlan_valid[0x1]; u8 vlan_id[0xc]; u8 source_mac_47_32[0x10]; u8 source_mac_31_0[0x20]; - u8 reserved_1[0x14]; + u8 reserved_at_c0[0x14]; u8 roce_l3_type[0x4]; u8 roce_version[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_e0[0x20]; }; union mlx5_ifc_hca_cap_union_bits { @@ -1904,7 +1904,7 @@ union mlx5_ifc_hca_cap_union_bits { struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap; struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap; struct mlx5_ifc_e_switch_cap_bits e_switch_cap; - u8 reserved_0[0x8000]; + u8 reserved_at_0[0x8000]; }; enum { @@ -1914,24 +1914,24 @@ enum { }; struct mlx5_ifc_flow_context_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 group_id[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 flow_tag[0x18]; - u8 reserved_2[0x10]; + u8 reserved_at_60[0x10]; u8 action[0x10]; - u8 reserved_3[0x8]; + u8 reserved_at_80[0x8]; u8 destination_list_size[0x18]; - u8 reserved_4[0x160]; + u8 reserved_at_a0[0x160]; struct mlx5_ifc_fte_match_param_bits match_value; - u8 reserved_5[0x600]; + u8 reserved_at_1200[0x600]; struct mlx5_ifc_dest_format_struct_bits destination[0]; }; @@ -1944,43 +1944,43 @@ enum { struct mlx5_ifc_xrc_srqc_bits { u8 state[0x4]; u8 log_xrc_srq_size[0x4]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; u8 basic_cyclic_rcv_wqe[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_2[0x2]; + u8 reserved_at_46[0x2]; u8 cqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 user_index_equal_xrc_srqn[0x1]; - u8 reserved_4[0x1]; + u8 reserved_at_81[0x1]; u8 log_page_size[0x6]; u8 user_index[0x18]; - u8 reserved_5[0x20]; + u8 reserved_at_a0[0x20]; - u8 reserved_6[0x8]; + u8 reserved_at_c0[0x8]; u8 pd[0x18]; u8 lwm[0x10]; u8 wqe_cnt[0x10]; - u8 reserved_7[0x40]; + u8 reserved_at_100[0x40]; u8 db_record_addr_h[0x20]; u8 db_record_addr_l[0x1e]; - u8 reserved_8[0x2]; + u8 reserved_at_17e[0x2]; - u8 reserved_9[0x80]; + u8 reserved_at_180[0x80]; }; struct mlx5_ifc_traffic_counter_bits { @@ -1990,16 +1990,16 @@ struct mlx5_ifc_traffic_counter_bits { }; struct mlx5_ifc_tisc_bits { - u8 reserved_0[0xc]; + u8 reserved_at_0[0xc]; u8 prio[0x4]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x100]; + u8 reserved_at_20[0x100]; - u8 reserved_3[0x8]; + u8 reserved_at_120[0x8]; u8 transport_domain[0x18]; - u8 reserved_4[0x3c0]; + u8 reserved_at_140[0x3c0]; }; enum { @@ -2024,31 +2024,31 @@ enum { }; struct mlx5_ifc_tirc_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 disp_type[0x4]; - u8 reserved_1[0x1c]; + u8 reserved_at_24[0x1c]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; - u8 reserved_3[0x4]; + u8 reserved_at_80[0x4]; u8 lro_timeout_period_usecs[0x10]; u8 lro_enable_mask[0x4]; u8 lro_max_ip_payload_size[0x8]; - u8 reserved_4[0x40]; + u8 reserved_at_a0[0x40]; - u8 reserved_5[0x8]; + u8 reserved_at_e0[0x8]; u8 inline_rqn[0x18]; u8 rx_hash_symmetric[0x1]; - u8 reserved_6[0x1]; + u8 reserved_at_101[0x1]; u8 tunneled_offload_en[0x1]; - u8 reserved_7[0x5]; + u8 reserved_at_103[0x5]; u8 indirect_table[0x18]; u8 rx_hash_fn[0x4]; - u8 reserved_8[0x2]; + u8 reserved_at_124[0x2]; u8 self_lb_block[0x2]; u8 transport_domain[0x18]; @@ -2058,7 +2058,7 @@ struct mlx5_ifc_tirc_bits { struct mlx5_ifc_rx_hash_field_select_bits rx_hash_field_selector_inner; - u8 reserved_9[0x4c0]; + u8 reserved_at_2c0[0x4c0]; }; enum { @@ -2069,39 +2069,39 @@ enum { struct mlx5_ifc_srqc_bits { u8 state[0x4]; u8 log_srq_size[0x4]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 wq_signature[0x1]; u8 cont_srq[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_22[0x1]; u8 rlky[0x1]; - u8 reserved_2[0x1]; + u8 reserved_at_24[0x1]; u8 log_rq_stride[0x3]; u8 xrcd[0x18]; u8 page_offset[0x6]; - u8 reserved_3[0x2]; + u8 reserved_at_46[0x2]; u8 cqn[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_60[0x20]; - u8 reserved_5[0x2]; + u8 reserved_at_80[0x2]; u8 log_page_size[0x6]; - u8 reserved_6[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_7[0x20]; + u8 reserved_at_a0[0x20]; - u8 reserved_8[0x8]; + u8 reserved_at_c0[0x8]; u8 pd[0x18]; u8 lwm[0x10]; u8 wqe_cnt[0x10]; - u8 reserved_9[0x40]; + u8 reserved_at_100[0x40]; u8 dbr_addr[0x40]; - u8 reserved_10[0x80]; + u8 reserved_at_180[0x80]; }; enum { @@ -2115,39 +2115,39 @@ struct mlx5_ifc_sqc_bits { u8 cd_master[0x1]; u8 fre[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 state[0x4]; - u8 reserved_1[0x14]; + u8 reserved_at_c[0x14]; - u8 reserved_2[0x8]; + u8 reserved_at_20[0x8]; u8 user_index[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_4[0xa0]; + u8 reserved_at_60[0xa0]; u8 tis_lst_sz[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_110[0x10]; - u8 reserved_6[0x40]; + u8 reserved_at_120[0x40]; - u8 reserved_7[0x8]; + u8 reserved_at_160[0x8]; u8 tis_num_0[0x18]; struct mlx5_ifc_wq_bits wq; }; struct mlx5_ifc_rqtc_bits { - u8 reserved_0[0xa0]; + u8 reserved_at_0[0xa0]; - u8 reserved_1[0x10]; + u8 reserved_at_a0[0x10]; u8 rqt_max_size[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_c0[0x10]; u8 rqt_actual_size[0x10]; - u8 reserved_3[0x6a0]; + u8 reserved_at_e0[0x6a0]; struct mlx5_ifc_rq_num_bits rq_num[0]; }; @@ -2165,27 +2165,27 @@ enum { struct mlx5_ifc_rqc_bits { u8 rlky[0x1]; - u8 reserved_0[0x2]; + u8 reserved_at_1[0x2]; u8 vsd[0x1]; u8 mem_rq_type[0x4]; u8 state[0x4]; - u8 reserved_1[0x1]; + u8 reserved_at_c[0x1]; u8 flush_in_error_en[0x1]; - u8 reserved_2[0x12]; + u8 reserved_at_e[0x12]; - u8 reserved_3[0x8]; + u8 reserved_at_20[0x8]; u8 user_index[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; u8 counter_set_id[0x8]; - u8 reserved_5[0x18]; + u8 reserved_at_68[0x18]; - u8 reserved_6[0x8]; + u8 reserved_at_80[0x8]; u8 rmpn[0x18]; - u8 reserved_7[0xe0]; + u8 reserved_at_a0[0xe0]; struct mlx5_ifc_wq_bits wq; }; @@ -2196,31 +2196,31 @@ enum { }; struct mlx5_ifc_rmpc_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 state[0x4]; - u8 reserved_1[0x14]; + u8 reserved_at_c[0x14]; u8 basic_cyclic_rcv_wqe[0x1]; - u8 reserved_2[0x1f]; + u8 reserved_at_21[0x1f]; - u8 reserved_3[0x140]; + u8 reserved_at_40[0x140]; struct mlx5_ifc_wq_bits wq; }; struct mlx5_ifc_nic_vport_context_bits { - u8 reserved_0[0x1f]; + u8 reserved_at_0[0x1f]; u8 roce_en[0x1]; u8 arm_change_event[0x1]; - u8 reserved_1[0x1a]; + u8 reserved_at_21[0x1a]; u8 event_on_mtu[0x1]; u8 event_on_promisc_change[0x1]; u8 event_on_vlan_change[0x1]; u8 event_on_mc_address_change[0x1]; u8 event_on_uc_address_change[0x1]; - u8 reserved_2[0xf0]; + u8 reserved_at_40[0xf0]; u8 mtu[0x10]; @@ -2228,21 +2228,21 @@ struct mlx5_ifc_nic_vport_context_bits { u8 port_guid[0x40]; u8 node_guid[0x40]; - u8 reserved_3[0x140]; + u8 reserved_at_200[0x140]; u8 qkey_violation_counter[0x10]; - u8 reserved_4[0x430]; + u8 reserved_at_350[0x430]; u8 promisc_uc[0x1]; u8 promisc_mc[0x1]; u8 promisc_all[0x1]; - u8 reserved_5[0x2]; + u8 reserved_at_783[0x2]; u8 allowed_list_type[0x3]; - u8 reserved_6[0xc]; + u8 reserved_at_788[0xc]; u8 allowed_list_size[0xc]; struct mlx5_ifc_mac_address_layout_bits permanent_address; - u8 reserved_7[0x20]; + u8 reserved_at_7e0[0x20]; u8 current_uc_mac_address[0][0x40]; }; @@ -2254,9 +2254,9 @@ enum { }; struct mlx5_ifc_mkc_bits { - u8 reserved_0[0x1]; + u8 reserved_at_0[0x1]; u8 free[0x1]; - u8 reserved_1[0xd]; + u8 reserved_at_2[0xd]; u8 small_fence_on_rdma_read_response[0x1]; u8 umr_en[0x1]; u8 a[0x1]; @@ -2265,19 +2265,19 @@ struct mlx5_ifc_mkc_bits { u8 lw[0x1]; u8 lr[0x1]; u8 access_mode[0x2]; - u8 reserved_2[0x8]; + u8 reserved_at_18[0x8]; u8 qpn[0x18]; u8 mkey_7_0[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_40[0x20]; u8 length64[0x1]; u8 bsf_en[0x1]; u8 sync_umr[0x1]; - u8 reserved_4[0x2]; + u8 reserved_at_63[0x2]; u8 expected_sigerr_count[0x1]; - u8 reserved_5[0x1]; + u8 reserved_at_66[0x1]; u8 en_rinval[0x1]; u8 pd[0x18]; @@ -2287,18 +2287,18 @@ struct mlx5_ifc_mkc_bits { u8 bsf_octword_size[0x20]; - u8 reserved_6[0x80]; + u8 reserved_at_120[0x80]; u8 translations_octword_size[0x20]; - u8 reserved_7[0x1b]; + u8 reserved_at_1c0[0x1b]; u8 log_page_size[0x5]; - u8 reserved_8[0x20]; + u8 reserved_at_1e0[0x20]; }; struct mlx5_ifc_pkey_bits { - u8 reserved_0[0x10]; + u8 reserved_at_0[0x10]; u8 pkey[0x10]; }; @@ -2309,19 +2309,19 @@ struct mlx5_ifc_array128_auto_bits { struct mlx5_ifc_hca_vport_context_bits { u8 field_select[0x20]; - u8 reserved_0[0xe0]; + u8 reserved_at_20[0xe0]; u8 sm_virt_aware[0x1]; u8 has_smi[0x1]; u8 has_raw[0x1]; u8 grh_required[0x1]; - u8 reserved_1[0xc]; + u8 reserved_at_104[0xc]; u8 port_physical_state[0x4]; u8 vport_state_policy[0x4]; u8 port_state[0x4]; u8 vport_state[0x4]; - u8 reserved_2[0x20]; + u8 reserved_at_120[0x20]; u8 system_image_guid[0x40]; @@ -2337,33 +2337,33 @@ struct mlx5_ifc_hca_vport_context_bits { u8 cap_mask2_field_select[0x20]; - u8 reserved_3[0x80]; + u8 reserved_at_280[0x80]; u8 lid[0x10]; - u8 reserved_4[0x4]; + u8 reserved_at_310[0x4]; u8 init_type_reply[0x4]; u8 lmc[0x3]; u8 subnet_timeout[0x5]; u8 sm_lid[0x10]; u8 sm_sl[0x4]; - u8 reserved_5[0xc]; + u8 reserved_at_334[0xc]; u8 qkey_violation_counter[0x10]; u8 pkey_violation_counter[0x10]; - u8 reserved_6[0xca0]; + u8 reserved_at_360[0xca0]; }; struct mlx5_ifc_esw_vport_context_bits { - u8 reserved_0[0x3]; + u8 reserved_at_0[0x3]; u8 vport_svlan_strip[0x1]; u8 vport_cvlan_strip[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_insert[0x2]; - u8 reserved_1[0x18]; + u8 reserved_at_8[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; u8 svlan_cfi[0x1]; u8 svlan_pcp[0x3]; @@ -2372,7 +2372,7 @@ struct mlx5_ifc_esw_vport_context_bits { u8 cvlan_pcp[0x3]; u8 cvlan_id[0xc]; - u8 reserved_3[0x7a0]; + u8 reserved_at_60[0x7a0]; }; enum { @@ -2387,41 +2387,41 @@ enum { struct mlx5_ifc_eqc_bits { u8 status[0x4]; - u8 reserved_0[0x9]; + u8 reserved_at_4[0x9]; u8 ec[0x1]; u8 oi[0x1]; - u8 reserved_1[0x5]; + u8 reserved_at_f[0x5]; u8 st[0x4]; - u8 reserved_2[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_4[0x14]; + u8 reserved_at_40[0x14]; u8 page_offset[0x6]; - u8 reserved_5[0x6]; + u8 reserved_at_5a[0x6]; - u8 reserved_6[0x3]; + u8 reserved_at_60[0x3]; u8 log_eq_size[0x5]; u8 uar_page[0x18]; - u8 reserved_7[0x20]; + u8 reserved_at_80[0x20]; - u8 reserved_8[0x18]; + u8 reserved_at_a0[0x18]; u8 intr[0x8]; - u8 reserved_9[0x3]; + u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; - u8 reserved_10[0x18]; + u8 reserved_at_c8[0x18]; - u8 reserved_11[0x60]; + u8 reserved_at_e0[0x60]; - u8 reserved_12[0x8]; + u8 reserved_at_140[0x8]; u8 consumer_counter[0x18]; - u8 reserved_13[0x8]; + u8 reserved_at_160[0x8]; u8 producer_counter[0x18]; - u8 reserved_14[0x80]; + u8 reserved_at_180[0x80]; }; enum { @@ -2445,14 +2445,14 @@ enum { }; struct mlx5_ifc_dctc_bits { - u8 reserved_0[0x4]; + u8 reserved_at_0[0x4]; u8 state[0x4]; - u8 reserved_1[0x18]; + u8 reserved_at_8[0x18]; - u8 reserved_2[0x8]; + u8 reserved_at_20[0x8]; u8 user_index[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; u8 counter_set_id[0x8]; @@ -2464,45 +2464,45 @@ struct mlx5_ifc_dctc_bits { u8 latency_sensitive[0x1]; u8 rlky[0x1]; u8 free_ar[0x1]; - u8 reserved_4[0xd]; + u8 reserved_at_73[0xd]; - u8 reserved_5[0x8]; + u8 reserved_at_80[0x8]; u8 cs_res[0x8]; - u8 reserved_6[0x3]; + u8 reserved_at_90[0x3]; u8 min_rnr_nak[0x5]; - u8 reserved_7[0x8]; + u8 reserved_at_98[0x8]; - u8 reserved_8[0x8]; + u8 reserved_at_a0[0x8]; u8 srqn[0x18]; - u8 reserved_9[0x8]; + u8 reserved_at_c0[0x8]; u8 pd[0x18]; u8 tclass[0x8]; - u8 reserved_10[0x4]; + u8 reserved_at_e8[0x4]; u8 flow_label[0x14]; u8 dc_access_key[0x40]; - u8 reserved_11[0x5]; + u8 reserved_at_140[0x5]; u8 mtu[0x3]; u8 port[0x8]; u8 pkey_index[0x10]; - u8 reserved_12[0x8]; + u8 reserved_at_160[0x8]; u8 my_addr_index[0x8]; - u8 reserved_13[0x8]; + u8 reserved_at_170[0x8]; u8 hop_limit[0x8]; u8 dc_access_key_violation_count[0x20]; - u8 reserved_14[0x14]; + u8 reserved_at_1a0[0x14]; u8 dei_cfi[0x1]; u8 eth_prio[0x3]; u8 ecn[0x2]; u8 dscp[0x6]; - u8 reserved_15[0x40]; + u8 reserved_at_1c0[0x40]; }; enum { @@ -2524,54 +2524,54 @@ enum { struct mlx5_ifc_cqc_bits { u8 status[0x4]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 cqe_sz[0x3]; u8 cc[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_c[0x1]; u8 scqe_break_moderation_en[0x1]; u8 oi[0x1]; - u8 reserved_2[0x2]; + u8 reserved_at_f[0x2]; u8 cqe_zip_en[0x1]; u8 mini_cqe_res_format[0x2]; u8 st[0x4]; - u8 reserved_3[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_4[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_5[0x14]; + u8 reserved_at_40[0x14]; u8 page_offset[0x6]; - u8 reserved_6[0x6]; + u8 reserved_at_5a[0x6]; - u8 reserved_7[0x3]; + u8 reserved_at_60[0x3]; u8 log_cq_size[0x5]; u8 uar_page[0x18]; - u8 reserved_8[0x4]; + u8 reserved_at_80[0x4]; u8 cq_period[0xc]; u8 cq_max_count[0x10]; - u8 reserved_9[0x18]; + u8 reserved_at_a0[0x18]; u8 c_eqn[0x8]; - u8 reserved_10[0x3]; + u8 reserved_at_c0[0x3]; u8 log_page_size[0x5]; - u8 reserved_11[0x18]; + u8 reserved_at_c8[0x18]; - u8 reserved_12[0x20]; + u8 reserved_at_e0[0x20]; - u8 reserved_13[0x8]; + u8 reserved_at_100[0x8]; u8 last_notified_index[0x18]; - u8 reserved_14[0x8]; + u8 reserved_at_120[0x8]; u8 last_solicit_index[0x18]; - u8 reserved_15[0x8]; + u8 reserved_at_140[0x8]; u8 consumer_counter[0x18]; - u8 reserved_16[0x8]; + u8 reserved_at_160[0x8]; u8 producer_counter[0x18]; - u8 reserved_17[0x40]; + u8 reserved_at_180[0x40]; u8 dbr_addr[0x40]; }; @@ -2580,16 +2580,16 @@ union mlx5_ifc_cong_control_roce_ecn_auto_bits { struct mlx5_ifc_cong_control_802_1qau_rp_bits cong_control_802_1qau_rp; struct mlx5_ifc_cong_control_r_roce_ecn_rp_bits cong_control_r_roce_ecn_rp; struct mlx5_ifc_cong_control_r_roce_ecn_np_bits cong_control_r_roce_ecn_np; - u8 reserved_0[0x800]; + u8 reserved_at_0[0x800]; }; struct mlx5_ifc_query_adapter_param_block_bits { - u8 reserved_0[0xc0]; + u8 reserved_at_0[0xc0]; - u8 reserved_1[0x8]; + u8 reserved_at_c0[0x8]; u8 ieee_vendor_id[0x18]; - u8 reserved_2[0x10]; + u8 reserved_at_e0[0x10]; u8 vsd_vendor_id[0x10]; u8 vsd[208][0x8]; @@ -2600,14 +2600,14 @@ struct mlx5_ifc_query_adapter_param_block_bits { union mlx5_ifc_modify_field_select_resize_field_select_auto_bits { struct mlx5_ifc_modify_field_select_bits modify_field_select; struct mlx5_ifc_resize_field_select_bits resize_field_select; - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; }; union mlx5_ifc_field_select_802_1_r_roce_auto_bits { struct mlx5_ifc_field_select_802_1qau_rp_bits field_select_802_1qau_rp; struct mlx5_ifc_field_select_r_roce_rp_bits field_select_r_roce_rp; struct mlx5_ifc_field_select_r_roce_np_bits field_select_r_roce_np; - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; }; union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { @@ -2619,7 +2619,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_eth_per_prio_grp_data_layout_bits eth_per_prio_grp_data_layout; struct mlx5_ifc_eth_per_traffic_grp_data_layout_bits eth_per_traffic_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; - u8 reserved_0[0x7c0]; + u8 reserved_at_0[0x7c0]; }; union mlx5_ifc_event_auto_bits { @@ -2635,23 +2635,23 @@ union mlx5_ifc_event_auto_bits { struct mlx5_ifc_db_bf_congestion_event_bits db_bf_congestion_event; struct mlx5_ifc_stall_vl_event_bits stall_vl_event; struct mlx5_ifc_cmd_inter_comp_event_bits cmd_inter_comp_event; - u8 reserved_0[0xe0]; + u8 reserved_at_0[0xe0]; }; struct mlx5_ifc_health_buffer_bits { - u8 reserved_0[0x100]; + u8 reserved_at_0[0x100]; u8 assert_existptr[0x20]; u8 assert_callra[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_140[0x40]; u8 fw_version[0x20]; u8 hw_id[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_1c0[0x20]; u8 irisc_index[0x8]; u8 synd[0x8]; @@ -2660,20 +2660,20 @@ struct mlx5_ifc_health_buffer_bits { struct mlx5_ifc_register_loopback_control_bits { u8 no_lb[0x1]; - u8 reserved_0[0x7]; + u8 reserved_at_1[0x7]; u8 port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_teardown_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -2683,108 +2683,108 @@ enum { struct mlx5_ifc_teardown_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 profile[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_sqerr2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_sqerr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_sqd2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_sqd2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_set_roce_address_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_roce_address_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 roce_address_index[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_50[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_roce_addr_layout_bits roce_address; }; struct mlx5_ifc_set_mad_demux_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -2794,89 +2794,89 @@ enum { struct mlx5_ifc_set_mad_demux_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x6]; + u8 reserved_at_60[0x6]; u8 demux_mode[0x2]; - u8 reserved_4[0x18]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_set_l2_table_entry_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_l2_table_entry_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_40[0x60]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 table_index[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_c0[0x20]; - u8 reserved_5[0x13]; + u8 reserved_at_e0[0x13]; u8 vlan_valid[0x1]; u8 vlan[0xc]; struct mlx5_ifc_mac_address_layout_bits mac_address; - u8 reserved_6[0xc0]; + u8 reserved_at_140[0xc0]; }; struct mlx5_ifc_set_issi_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_issi_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 current_issi[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_set_hca_cap_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_hca_cap_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; union mlx5_ifc_hca_cap_union_bits capability; }; @@ -2890,156 +2890,156 @@ enum { struct mlx5_ifc_set_fte_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_fte_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x18]; + u8 reserved_at_c0[0x18]; u8 modify_enable_mask[0x8]; - u8 reserved_6[0x20]; + u8 reserved_at_e0[0x20]; u8 flow_index[0x20]; - u8 reserved_7[0xe0]; + u8 reserved_at_120[0xe0]; struct mlx5_ifc_flow_context_bits flow_context; }; struct mlx5_ifc_rts2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rts2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_rtr2rts_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rtr2rts_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_rst2init_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rst2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_query_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; enum { @@ -3049,13 +3049,13 @@ enum { struct mlx5_ifc_query_vport_state_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_2[0x18]; + u8 reserved_at_60[0x18]; u8 admin_state[0x4]; u8 state[0x4]; }; @@ -3067,25 +3067,25 @@ enum { struct mlx5_ifc_query_vport_state_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_vport_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_traffic_counter_bits received_errors; @@ -3111,7 +3111,7 @@ struct mlx5_ifc_query_vport_counter_out_bits { struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast; - u8 reserved_2[0xa00]; + u8 reserved_at_680[0xa00]; }; enum { @@ -3120,328 +3120,328 @@ enum { struct mlx5_ifc_query_vport_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x60]; + u8 reserved_at_60[0x60]; u8 clear[0x1]; - u8 reserved_4[0x1f]; + u8 reserved_at_c1[0x1f]; - u8 reserved_5[0x20]; + u8 reserved_at_e0[0x20]; }; struct mlx5_ifc_query_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_tisc_bits tis_context; }; struct mlx5_ifc_query_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_tirc_bits tir_context; }; struct mlx5_ifc_query_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_srqc_bits srq_context_entry; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_sqc_bits sq_context; }; struct mlx5_ifc_query_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 sqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_special_contexts_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; u8 resd_lkey[0x20]; }; struct mlx5_ifc_query_special_contexts_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqtc_bits rqt_context; }; struct mlx5_ifc_query_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqc_bits rq_context; }; struct mlx5_ifc_query_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_roce_address_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_roce_addr_layout_bits roce_address; }; struct mlx5_ifc_query_roce_address_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 roce_address_index[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_50[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rmpc_bits rmp_context; }; struct mlx5_ifc_query_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rmpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_3[0x80]; + u8 reserved_at_800[0x80]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_q_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 rx_write_requests[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_a0[0x20]; u8 rx_read_requests[0x20]; - u8 reserved_3[0x20]; + u8 reserved_at_e0[0x20]; u8 rx_atomic_requests[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_120[0x20]; u8 rx_dct_connect[0x20]; - u8 reserved_5[0x20]; + u8 reserved_at_160[0x20]; u8 out_of_buffer[0x20]; - u8 reserved_6[0x20]; + u8 reserved_at_1a0[0x20]; u8 out_of_sequence[0x20]; - u8 reserved_7[0x620]; + u8 reserved_at_1e0[0x620]; }; struct mlx5_ifc_query_q_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x80]; + u8 reserved_at_40[0x80]; u8 clear[0x1]; - u8 reserved_3[0x1f]; + u8 reserved_at_c1[0x1f]; - u8 reserved_4[0x18]; + u8 reserved_at_e0[0x18]; u8 counter_set_id[0x8]; }; struct mlx5_ifc_query_pages_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; u8 num_pages[0x20]; @@ -3455,55 +3455,55 @@ enum { struct mlx5_ifc_query_pages_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_nic_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_nic_vport_context_bits nic_vport_context; }; struct mlx5_ifc_query_nic_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x5]; + u8 reserved_at_60[0x5]; u8 allowed_list_type[0x3]; - u8 reserved_4[0x18]; + u8 reserved_at_68[0x18]; }; struct mlx5_ifc_query_mkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 bsf0_klm0_pas_mtt0_1[16][0x8]; @@ -3512,265 +3512,265 @@ struct mlx5_ifc_query_mkey_out_bits { struct mlx5_ifc_query_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 mkey_index[0x18]; u8 pg_access[0x1]; - u8 reserved_3[0x1f]; + u8 reserved_at_61[0x1f]; }; struct mlx5_ifc_query_mad_demux_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 mad_dumux_parameters_block[0x20]; }; struct mlx5_ifc_query_mad_demux_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_l2_table_entry_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xa0]; + u8 reserved_at_40[0xa0]; - u8 reserved_2[0x13]; + u8 reserved_at_e0[0x13]; u8 vlan_valid[0x1]; u8 vlan[0xc]; struct mlx5_ifc_mac_address_layout_bits mac_address; - u8 reserved_3[0xc0]; + u8 reserved_at_140[0xc0]; }; struct mlx5_ifc_query_l2_table_entry_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_40[0x60]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 table_index[0x18]; - u8 reserved_4[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_query_issi_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x10]; + u8 reserved_at_40[0x10]; u8 current_issi[0x10]; - u8 reserved_2[0xa0]; + u8 reserved_at_60[0xa0]; - u8 supported_issi_reserved[76][0x8]; + u8 reserved_at_100[76][0x8]; u8 supported_issi_dw0[0x20]; }; struct mlx5_ifc_query_issi_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_hca_vport_pkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_pkey_bits pkey[0]; }; struct mlx5_ifc_query_hca_vport_pkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 pkey_index[0x10]; }; struct mlx5_ifc_query_hca_vport_gid_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; u8 gids_num[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_70[0x10]; struct mlx5_ifc_array128_auto_bits gid[0]; }; struct mlx5_ifc_query_hca_vport_gid_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 gid_index[0x10]; }; struct mlx5_ifc_query_hca_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_hca_vport_context_bits hca_vport_context; }; struct mlx5_ifc_query_hca_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_hca_cap_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; union mlx5_ifc_hca_cap_union_bits capability; }; struct mlx5_ifc_query_hca_cap_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_query_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x80]; + u8 reserved_at_40[0x80]; - u8 reserved_2[0x8]; + u8 reserved_at_c0[0x8]; u8 level[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_d0[0x8]; u8 log_size[0x8]; - u8 reserved_4[0x120]; + u8 reserved_at_e0[0x120]; }; struct mlx5_ifc_query_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_query_fte_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x1c0]; + u8 reserved_at_40[0x1c0]; struct mlx5_ifc_flow_context_bits flow_context; }; struct mlx5_ifc_query_fte_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x40]; + u8 reserved_at_c0[0x40]; u8 flow_index[0x20]; - u8 reserved_6[0xe0]; + u8 reserved_at_120[0xe0]; }; enum { @@ -3781,84 +3781,84 @@ enum { struct mlx5_ifc_query_flow_group_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0xa0]; + u8 reserved_at_40[0xa0]; u8 start_flow_index[0x20]; - u8 reserved_2[0x20]; + u8 reserved_at_100[0x20]; u8 end_flow_index[0x20]; - u8 reserved_3[0xa0]; + u8 reserved_at_140[0xa0]; - u8 reserved_4[0x18]; + u8 reserved_at_1e0[0x18]; u8 match_criteria_enable[0x8]; struct mlx5_ifc_fte_match_param_bits match_criteria; - u8 reserved_5[0xe00]; + u8 reserved_at_1200[0xe00]; }; struct mlx5_ifc_query_flow_group_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; u8 group_id[0x20]; - u8 reserved_5[0x120]; + u8 reserved_at_e0[0x120]; }; struct mlx5_ifc_query_esw_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_esw_vport_context_bits esw_vport_context; }; struct mlx5_ifc_query_esw_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_modify_esw_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_esw_vport_context_fields_select_bits { - u8 reserved[0x1c]; + u8 reserved_at_0[0x1c]; u8 vport_cvlan_insert[0x1]; u8 vport_svlan_insert[0x1]; u8 vport_cvlan_strip[0x1]; @@ -3867,13 +3867,13 @@ struct mlx5_ifc_esw_vport_context_fields_select_bits { struct mlx5_ifc_modify_esw_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; struct mlx5_ifc_esw_vport_context_fields_select_bits field_select; @@ -3883,124 +3883,124 @@ struct mlx5_ifc_modify_esw_vport_context_in_bits { struct mlx5_ifc_query_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_eqc_bits eq_context_entry; - u8 reserved_2[0x40]; + u8 reserved_at_280[0x40]; u8 event_bitmask[0x40]; - u8 reserved_3[0x580]; + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_eq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_dctc_bits dct_context_entry; - u8 reserved_2[0x180]; + u8 reserved_at_280[0x180]; }; struct mlx5_ifc_query_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_2[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_query_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cong_status_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; u8 enable[0x1]; u8 tag_enable[0x1]; - u8 reserved_2[0x1e]; + u8 reserved_at_62[0x1e]; }; struct mlx5_ifc_query_cong_status_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 priority[0x4]; u8 cong_protocol[0x4]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cong_statistics_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 cur_flows[0x20]; @@ -4014,7 +4014,7 @@ struct mlx5_ifc_query_cong_statistics_out_bits { u8 cnp_handled_low[0x20]; - u8 reserved_2[0x100]; + u8 reserved_at_140[0x100]; u8 time_stamp_high[0x20]; @@ -4030,453 +4030,453 @@ struct mlx5_ifc_query_cong_statistics_out_bits { u8 cnps_sent_low[0x20]; - u8 reserved_3[0x560]; + u8 reserved_at_320[0x560]; }; struct mlx5_ifc_query_cong_statistics_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 clear[0x1]; - u8 reserved_2[0x1f]; + u8 reserved_at_41[0x1f]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_cong_params_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; }; struct mlx5_ifc_query_cong_params_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x1c]; + u8 reserved_at_40[0x1c]; u8 cong_protocol[0x4]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_query_adapter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_query_adapter_param_block_bits query_adapter_struct; }; struct mlx5_ifc_query_adapter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_qp_2rst_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_qp_2rst_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_qp_2err_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_qp_2err_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_page_fault_resume_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_page_fault_resume_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 error[0x1]; - u8 reserved_2[0x4]; + u8 reserved_at_41[0x4]; u8 rdma[0x1]; u8 read_write[0x1]; u8 req_res[0x1]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_nop_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_nop_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_vport_state_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_vport_state_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; - u8 reserved_3[0x18]; + u8 reserved_at_60[0x18]; u8 admin_state[0x4]; - u8 reserved_4[0x4]; + u8 reserved_at_7c[0x4]; }; struct mlx5_ifc_modify_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_tis_bitmask_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved_1[0x1f]; + u8 reserved_at_20[0x1f]; u8 prio[0x1]; }; struct mlx5_ifc_modify_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_modify_tis_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_tisc_bits ctx; }; struct mlx5_ifc_modify_tir_bitmask_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved_1[0x1b]; + u8 reserved_at_20[0x1b]; u8 self_lb_en[0x1]; - u8 reserved_2[0x3]; + u8 reserved_at_3c[0x3]; u8 lro[0x1]; }; struct mlx5_ifc_modify_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_modify_tir_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_tirc_bits ctx; }; struct mlx5_ifc_modify_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 sq_state[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 sqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 modify_bitmask[0x40]; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_sqc_bits ctx; }; struct mlx5_ifc_modify_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rqt_bitmask_bits { - u8 reserved[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved1[0x1f]; + u8 reserved_at_20[0x1f]; u8 rqn_list[0x1]; }; struct mlx5_ifc_modify_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_rqt_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_rqtc_bits ctx; }; struct mlx5_ifc_modify_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 rq_state[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 rqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 modify_bitmask[0x40]; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_rqc_bits ctx; }; struct mlx5_ifc_modify_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_rmp_bitmask_bits { - u8 reserved[0x20]; + u8 reserved_at_0[0x20]; - u8 reserved1[0x1f]; + u8 reserved_at_20[0x1f]; u8 lwm[0x1]; }; struct mlx5_ifc_modify_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 rmp_state[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 rmpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_rmp_bitmask_bits bitmask; - u8 reserved_4[0x40]; + u8 reserved_at_c0[0x40]; struct mlx5_ifc_rmpc_bits ctx; }; struct mlx5_ifc_modify_nic_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_nic_vport_field_select_bits { - u8 reserved_0[0x19]; + u8 reserved_at_0[0x19]; u8 mtu[0x1]; u8 change_event[0x1]; u8 promisc[0x1]; u8 permanent_address[0x1]; u8 addresses_list[0x1]; u8 roce_en[0x1]; - u8 reserved_1[0x1]; + u8 reserved_at_1f[0x1]; }; struct mlx5_ifc_modify_nic_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xf]; + u8 reserved_at_41[0xf]; u8 vport_number[0x10]; struct mlx5_ifc_modify_nic_vport_field_select_bits field_select; - u8 reserved_3[0x780]; + u8 reserved_at_80[0x780]; struct mlx5_ifc_nic_vport_context_bits nic_vport_context; }; struct mlx5_ifc_modify_hca_vport_context_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_hca_vport_context_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_2[0xb]; + u8 reserved_at_41[0xb]; u8 port_num[0x4]; u8 vport_number[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; struct mlx5_ifc_hca_vport_context_bits hca_vport_context; }; struct mlx5_ifc_modify_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -4486,83 +4486,83 @@ enum { struct mlx5_ifc_modify_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; union mlx5_ifc_modify_field_select_resize_field_select_auto_bits modify_field_select_resize_field_select; struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_modify_cong_status_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_cong_status_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 priority[0x4]; u8 cong_protocol[0x4]; u8 enable[0x1]; u8 tag_enable[0x1]; - u8 reserved_3[0x1e]; + u8 reserved_at_62[0x1e]; }; struct mlx5_ifc_modify_cong_params_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_cong_params_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x1c]; + u8 reserved_at_40[0x1c]; u8 cong_protocol[0x4]; union mlx5_ifc_field_select_802_1_r_roce_auto_bits field_select; - u8 reserved_3[0x80]; + u8 reserved_at_80[0x80]; union mlx5_ifc_cong_control_roce_ecn_auto_bits congestion_parameters; }; struct mlx5_ifc_manage_pages_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; u8 output_num_entries[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_60[0x20]; u8 pas[0][0x40]; }; @@ -4575,12 +4575,12 @@ enum { struct mlx5_ifc_manage_pages_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; u8 input_num_entries[0x20]; @@ -4590,117 +4590,117 @@ struct mlx5_ifc_manage_pages_in_bits { struct mlx5_ifc_mad_ifc_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 response_mad_packet[256][0x8]; }; struct mlx5_ifc_mad_ifc_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 remote_lid[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_50[0x8]; u8 port[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 mad[256][0x8]; }; struct mlx5_ifc_init_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init2rtr_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init2rtr_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_init2init_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_init2init_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 opt_param_mask[0x20]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_5[0x80]; + u8 reserved_at_800[0x80]; }; struct mlx5_ifc_get_dropped_packet_log_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 packet_headers_log[128][0x8]; @@ -4709,1029 +4709,1029 @@ struct mlx5_ifc_get_dropped_packet_log_out_bits { struct mlx5_ifc_get_dropped_packet_log_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_gen_eqe_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 eqe[64][0x8]; }; struct mlx5_ifc_gen_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_enable_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; }; struct mlx5_ifc_enable_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_drain_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_drain_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_disable_hca_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x20]; + u8 reserved_at_40[0x20]; }; struct mlx5_ifc_disable_hca_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 function_id[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_detach_from_mcg_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_detach_from_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 multicast_gid[16][0x8]; }; struct mlx5_ifc_destroy_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 srqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 sqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 rmpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_psv_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_psv_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 psvn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_mkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 mkey_index[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_destroy_flow_group_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_flow_group_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; u8 group_id[0x20]; - u8 reserved_5[0x120]; + u8 reserved_at_e0[0x120]; }; struct mlx5_ifc_destroy_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_eq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_destroy_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_destroy_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_delete_vxlan_udp_dport_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_delete_vxlan_udp_dport_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 vxlan_udp_port[0x10]; }; struct mlx5_ifc_delete_l2_table_entry_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_delete_l2_table_entry_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_40[0x60]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 table_index[0x18]; - u8 reserved_4[0x140]; + u8 reserved_at_c0[0x140]; }; struct mlx5_ifc_delete_fte_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_delete_fte_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x40]; + u8 reserved_at_c0[0x40]; u8 flow_index[0x20]; - u8 reserved_6[0xe0]; + u8 reserved_at_120[0xe0]; }; struct mlx5_ifc_dealloc_xrcd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrcd[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_uar_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_uar_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 uar[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_transport_domain_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_transport_domain_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 transport_domain[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_q_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_q_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_40[0x18]; u8 counter_set_id[0x8]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_dealloc_pd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_dealloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 pd[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_xrc_srqc_bits xrc_srq_context_entry; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_tis_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 tisn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_tis_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_tisc_bits ctx; }; struct mlx5_ifc_create_tir_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 tirn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_tir_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_tirc_bits ctx; }; struct mlx5_ifc_create_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 srqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_srqc_bits srq_context_entry; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_sq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 sqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_sq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_sqc_bits ctx; }; struct mlx5_ifc_create_rqt_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 rqtn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_rqt_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqtc_bits rqt_context; }; struct mlx5_ifc_create_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 rqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rqc_bits ctx; }; struct mlx5_ifc_create_rmp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 rmpn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_rmp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0xc0]; + u8 reserved_at_40[0xc0]; struct mlx5_ifc_rmpc_bits ctx; }; struct mlx5_ifc_create_qp_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_qp_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 opt_param_mask[0x20]; - u8 reserved_3[0x20]; + u8 reserved_at_a0[0x20]; struct mlx5_ifc_qpc_bits qpc; - u8 reserved_4[0x80]; + u8 reserved_at_800[0x80]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_psv_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; - u8 reserved_2[0x8]; + u8 reserved_at_80[0x8]; u8 psv0_index[0x18]; - u8 reserved_3[0x8]; + u8 reserved_at_a0[0x8]; u8 psv1_index[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_c0[0x8]; u8 psv2_index[0x18]; - u8 reserved_5[0x8]; + u8 reserved_at_e0[0x8]; u8 psv3_index[0x18]; }; struct mlx5_ifc_create_psv_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 num_psv[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_44[0x4]; u8 pd[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_mkey_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 mkey_index[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_mkey_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; u8 pg_access[0x1]; - u8 reserved_3[0x1f]; + u8 reserved_at_61[0x1f]; struct mlx5_ifc_mkc_bits memory_key_mkey_entry; - u8 reserved_4[0x80]; + u8 reserved_at_280[0x80]; u8 translations_octword_actual_size[0x20]; - u8 reserved_5[0x560]; + u8 reserved_at_320[0x560]; u8 klm_pas_mtt[0][0x20]; }; struct mlx5_ifc_create_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 table_id[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_a0[0x20]; - u8 reserved_5[0x4]; + u8 reserved_at_c0[0x4]; u8 table_miss_mode[0x4]; u8 level[0x8]; - u8 reserved_6[0x8]; + u8 reserved_at_d0[0x8]; u8 log_size[0x8]; - u8 reserved_7[0x8]; + u8 reserved_at_e0[0x8]; u8 table_miss_id[0x18]; - u8 reserved_8[0x100]; + u8 reserved_at_100[0x100]; }; struct mlx5_ifc_create_flow_group_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 group_id[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; enum { @@ -5742,134 +5742,134 @@ enum { struct mlx5_ifc_create_flow_group_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x20]; + u8 reserved_at_c0[0x20]; u8 start_flow_index[0x20]; - u8 reserved_6[0x20]; + u8 reserved_at_100[0x20]; u8 end_flow_index[0x20]; - u8 reserved_7[0xa0]; + u8 reserved_at_140[0xa0]; - u8 reserved_8[0x18]; + u8 reserved_at_1e0[0x18]; u8 match_criteria_enable[0x8]; struct mlx5_ifc_fte_match_param_bits match_criteria; - u8 reserved_9[0xe00]; + u8 reserved_at_1200[0xe00]; }; struct mlx5_ifc_create_eq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x18]; + u8 reserved_at_40[0x18]; u8 eq_number[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_eq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_eqc_bits eq_context_entry; - u8 reserved_3[0x40]; + u8 reserved_at_280[0x40]; u8 event_bitmask[0x40]; - u8 reserved_4[0x580]; + u8 reserved_at_300[0x580]; u8 pas[0][0x40]; }; struct mlx5_ifc_create_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 dctn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_dctc_bits dct_context_entry; - u8 reserved_3[0x180]; + u8 reserved_at_280[0x180]; }; struct mlx5_ifc_create_cq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 cqn[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_create_cq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; struct mlx5_ifc_cqc_bits cq_context; - u8 reserved_3[0x600]; + u8 reserved_at_280[0x600]; u8 pas[0][0x40]; }; struct mlx5_ifc_config_int_moderation_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x4]; + u8 reserved_at_40[0x4]; u8 min_delay[0xc]; u8 int_vector[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; enum { @@ -5879,49 +5879,49 @@ enum { struct mlx5_ifc_config_int_moderation_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x4]; + u8 reserved_at_40[0x4]; u8 min_delay[0xc]; u8 int_vector[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_attach_to_mcg_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_attach_to_mcg_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 qpn[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; u8 multicast_gid[16][0x8]; }; struct mlx5_ifc_arm_xrc_srq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -5930,25 +5930,25 @@ enum { struct mlx5_ifc_arm_xrc_srq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 xrc_srqn[0x18]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 lwm[0x10]; }; struct mlx5_ifc_arm_rq_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; enum { @@ -5957,179 +5957,179 @@ enum { struct mlx5_ifc_arm_rq_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 srq_number[0x18]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 lwm[0x10]; }; struct mlx5_ifc_arm_dct_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_arm_dct_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_40[0x8]; u8 dct_number[0x18]; - u8 reserved_3[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_xrcd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 xrcd[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_xrcd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_uar_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 uar[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_uar_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_transport_domain_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 transport_domain[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_transport_domain_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_q_counter_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x18]; + u8 reserved_at_40[0x18]; u8 counter_set_id[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_q_counter_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_alloc_pd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x8]; + u8 reserved_at_40[0x8]; u8 pd[0x18]; - u8 reserved_2[0x20]; + u8 reserved_at_60[0x20]; }; struct mlx5_ifc_alloc_pd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_add_vxlan_udp_dport_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_add_vxlan_udp_dport_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 vxlan_udp_port[0x10]; }; struct mlx5_ifc_access_register_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; u8 register_data[0][0x20]; }; @@ -6141,12 +6141,12 @@ enum { struct mlx5_ifc_access_register_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_40[0x10]; u8 register_id[0x10]; u8 argument[0x20]; @@ -6159,24 +6159,24 @@ struct mlx5_ifc_sltp_reg_bits { u8 version[0x4]; u8 local_port[0x8]; u8 pnat[0x2]; - u8 reserved_0[0x2]; + u8 reserved_at_12[0x2]; u8 lane[0x4]; - u8 reserved_1[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_3[0x7]; + u8 reserved_at_40[0x7]; u8 polarity[0x1]; u8 ob_tap0[0x8]; u8 ob_tap1[0x8]; u8 ob_tap2[0x8]; - u8 reserved_4[0xc]; + u8 reserved_at_60[0xc]; u8 ob_preemp_mode[0x4]; u8 ob_reg[0x8]; u8 ob_bias[0x8]; - u8 reserved_5[0x20]; + u8 reserved_at_80[0x20]; }; struct mlx5_ifc_slrg_reg_bits { @@ -6184,36 +6184,36 @@ struct mlx5_ifc_slrg_reg_bits { u8 version[0x4]; u8 local_port[0x8]; u8 pnat[0x2]; - u8 reserved_0[0x2]; + u8 reserved_at_12[0x2]; u8 lane[0x4]; - u8 reserved_1[0x8]; + u8 reserved_at_18[0x8]; u8 time_to_link_up[0x10]; - u8 reserved_2[0xc]; + u8 reserved_at_30[0xc]; u8 grade_lane_speed[0x4]; u8 grade_version[0x8]; u8 grade[0x18]; - u8 reserved_3[0x4]; + u8 reserved_at_60[0x4]; u8 height_grade_type[0x4]; u8 height_grade[0x18]; u8 height_dz[0x10]; u8 height_dv[0x10]; - u8 reserved_4[0x10]; + u8 reserved_at_a0[0x10]; u8 height_sigma[0x10]; - u8 reserved_5[0x20]; + u8 reserved_at_c0[0x20]; - u8 reserved_6[0x4]; + u8 reserved_at_e0[0x4]; u8 phase_grade_type[0x4]; u8 phase_grade[0x18]; - u8 reserved_7[0x8]; + u8 reserved_at_100[0x8]; u8 phase_eo_pos[0x8]; - u8 reserved_8[0x8]; + u8 reserved_at_110[0x8]; u8 phase_eo_neg[0x8]; u8 ffe_set_tested[0x10]; @@ -6221,70 +6221,70 @@ struct mlx5_ifc_slrg_reg_bits { }; struct mlx5_ifc_pvlc_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x1c]; + u8 reserved_at_20[0x1c]; u8 vl_hw_cap[0x4]; - u8 reserved_3[0x1c]; + u8 reserved_at_40[0x1c]; u8 vl_admin[0x4]; - u8 reserved_4[0x1c]; + u8 reserved_at_60[0x1c]; u8 vl_operational[0x4]; }; struct mlx5_ifc_pude_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; - u8 reserved_0[0x4]; + u8 reserved_at_10[0x4]; u8 admin_status[0x4]; - u8 reserved_1[0x4]; + u8 reserved_at_18[0x4]; u8 oper_status[0x4]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_ptys_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0xd]; + u8 reserved_at_10[0xd]; u8 proto_mask[0x3]; - u8 reserved_2[0x40]; + u8 reserved_at_20[0x40]; u8 eth_proto_capability[0x20]; u8 ib_link_width_capability[0x10]; u8 ib_proto_capability[0x10]; - u8 reserved_3[0x20]; + u8 reserved_at_a0[0x20]; u8 eth_proto_admin[0x20]; u8 ib_link_width_admin[0x10]; u8 ib_proto_admin[0x10]; - u8 reserved_4[0x20]; + u8 reserved_at_100[0x20]; u8 eth_proto_oper[0x20]; u8 ib_link_width_oper[0x10]; u8 ib_proto_oper[0x10]; - u8 reserved_5[0x20]; + u8 reserved_at_160[0x20]; u8 eth_proto_lp_advertise[0x20]; - u8 reserved_6[0x60]; + u8 reserved_at_1a0[0x60]; }; struct mlx5_ifc_ptas_reg_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 algorithm_options[0x10]; - u8 reserved_1[0x4]; + u8 reserved_at_30[0x4]; u8 repetitions_mode[0x4]; u8 num_of_repetitions[0x8]; @@ -6310,13 +6310,13 @@ struct mlx5_ifc_ptas_reg_bits { u8 ndeo_error_threshold[0x10]; u8 mixer_offset_step_size[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_110[0x8]; u8 mix90_phase_for_voltage_bath[0x8]; u8 mixer_offset_start[0x10]; u8 mixer_offset_end[0x10]; - u8 reserved_3[0x15]; + u8 reserved_at_140[0x15]; u8 ber_test_time[0xb]; }; @@ -6324,154 +6324,154 @@ struct mlx5_ifc_pspa_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; u8 sub_port[0x8]; - u8 reserved_0[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_1[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_pqdr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x5]; + u8 reserved_at_10[0x5]; u8 prio[0x3]; - u8 reserved_2[0x6]; + u8 reserved_at_18[0x6]; u8 mode[0x2]; - u8 reserved_3[0x20]; + u8 reserved_at_20[0x20]; - u8 reserved_4[0x10]; + u8 reserved_at_40[0x10]; u8 min_threshold[0x10]; - u8 reserved_5[0x10]; + u8 reserved_at_60[0x10]; u8 max_threshold[0x10]; - u8 reserved_6[0x10]; + u8 reserved_at_80[0x10]; u8 mark_probability_denominator[0x10]; - u8 reserved_7[0x60]; + u8 reserved_at_a0[0x60]; }; struct mlx5_ifc_ppsc_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; - u8 reserved_3[0x1c]; + u8 reserved_at_80[0x1c]; u8 wrps_admin[0x4]; - u8 reserved_4[0x1c]; + u8 reserved_at_a0[0x1c]; u8 wrps_status[0x4]; - u8 reserved_5[0x8]; + u8 reserved_at_c0[0x8]; u8 up_threshold[0x8]; - u8 reserved_6[0x8]; + u8 reserved_at_d0[0x8]; u8 down_threshold[0x8]; - u8 reserved_7[0x20]; + u8 reserved_at_e0[0x20]; - u8 reserved_8[0x1c]; + u8 reserved_at_100[0x1c]; u8 srps_admin[0x4]; - u8 reserved_9[0x1c]; + u8 reserved_at_120[0x1c]; u8 srps_status[0x4]; - u8 reserved_10[0x40]; + u8 reserved_at_140[0x40]; }; struct mlx5_ifc_pplr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x8]; + u8 reserved_at_20[0x8]; u8 lb_cap[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_30[0x8]; u8 lb_en[0x8]; }; struct mlx5_ifc_pplm_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; u8 port_profile_mode[0x8]; u8 static_port_profile[0x8]; u8 active_port_profile[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_58[0x8]; u8 retransmission_active[0x8]; u8 fec_mode_active[0x18]; - u8 reserved_4[0x20]; + u8 reserved_at_80[0x20]; }; struct mlx5_ifc_ppcnt_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; u8 pnat[0x2]; - u8 reserved_0[0x8]; + u8 reserved_at_12[0x8]; u8 grp[0x6]; u8 clr[0x1]; - u8 reserved_1[0x1c]; + u8 reserved_at_21[0x1c]; u8 prio_tc[0x3]; union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set; }; struct mlx5_ifc_ppad_reg_bits { - u8 reserved_0[0x3]; + u8 reserved_at_0[0x3]; u8 single_mac[0x1]; - u8 reserved_1[0x4]; + u8 reserved_at_4[0x4]; u8 local_port[0x8]; u8 mac_47_32[0x10]; u8 mac_31_0[0x20]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_pmtu_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 max_mtu[0x10]; - u8 reserved_2[0x10]; + u8 reserved_at_30[0x10]; u8 admin_mtu[0x10]; - u8 reserved_3[0x10]; + u8 reserved_at_50[0x10]; u8 oper_mtu[0x10]; - u8 reserved_4[0x10]; + u8 reserved_at_70[0x10]; }; struct mlx5_ifc_pmpr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 module[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0x18]; + u8 reserved_at_20[0x18]; u8 attenuation_5g[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_40[0x18]; u8 attenuation_7g[0x8]; - u8 reserved_4[0x18]; + u8 reserved_at_60[0x18]; u8 attenuation_12g[0x8]; }; struct mlx5_ifc_pmpe_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 module[0x8]; - u8 reserved_1[0xc]; + u8 reserved_at_10[0xc]; u8 module_status[0x4]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_pmpc_reg_bits { @@ -6479,20 +6479,20 @@ struct mlx5_ifc_pmpc_reg_bits { }; struct mlx5_ifc_pmlpn_reg_bits { - u8 reserved_0[0x4]; + u8 reserved_at_0[0x4]; u8 mlpn_status[0x4]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 e[0x1]; - u8 reserved_2[0x1f]; + u8 reserved_at_21[0x1f]; }; struct mlx5_ifc_pmlp_reg_bits { u8 rxtx[0x1]; - u8 reserved_0[0x7]; + u8 reserved_at_1[0x7]; u8 local_port[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_10[0x8]; u8 width[0x8]; u8 lane0_module_mapping[0x20]; @@ -6503,36 +6503,36 @@ struct mlx5_ifc_pmlp_reg_bits { u8 lane3_module_mapping[0x20]; - u8 reserved_2[0x160]; + u8 reserved_at_a0[0x160]; }; struct mlx5_ifc_pmaos_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 module[0x8]; - u8 reserved_1[0x4]; + u8 reserved_at_10[0x4]; u8 admin_status[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_18[0x4]; u8 oper_status[0x4]; u8 ase[0x1]; u8 ee[0x1]; - u8 reserved_3[0x1c]; + u8 reserved_at_22[0x1c]; u8 e[0x2]; - u8 reserved_4[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_plpc_reg_bits { - u8 reserved_0[0x4]; + u8 reserved_at_0[0x4]; u8 profile_id[0xc]; - u8 reserved_1[0x4]; + u8 reserved_at_10[0x4]; u8 proto_mask[0x4]; - u8 reserved_2[0x8]; + u8 reserved_at_18[0x8]; - u8 reserved_3[0x10]; + u8 reserved_at_20[0x10]; u8 lane_speed[0x10]; - u8 reserved_4[0x17]; + u8 reserved_at_40[0x17]; u8 lpbf[0x1]; u8 fec_mode_policy[0x8]; @@ -6545,44 +6545,44 @@ struct mlx5_ifc_plpc_reg_bits { u8 retransmission_request_admin[0x8]; u8 fec_mode_request_admin[0x18]; - u8 reserved_5[0x80]; + u8 reserved_at_c0[0x80]; }; struct mlx5_ifc_plib_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_10[0x8]; u8 ib_port[0x8]; - u8 reserved_2[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_plbf_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0xd]; + u8 reserved_at_10[0xd]; u8 lbf_mode[0x3]; - u8 reserved_2[0x20]; + u8 reserved_at_20[0x20]; }; struct mlx5_ifc_pipg_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 dic[0x1]; - u8 reserved_2[0x19]; + u8 reserved_at_21[0x19]; u8 ipg[0x4]; - u8 reserved_3[0x2]; + u8 reserved_at_3e[0x2]; }; struct mlx5_ifc_pifr_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0xe0]; + u8 reserved_at_20[0xe0]; u8 port_filter[8][0x20]; @@ -6590,36 +6590,36 @@ struct mlx5_ifc_pifr_reg_bits { }; struct mlx5_ifc_pfcc_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 ppan[0x4]; - u8 reserved_2[0x4]; + u8 reserved_at_24[0x4]; u8 prio_mask_tx[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_30[0x8]; u8 prio_mask_rx[0x8]; u8 pptx[0x1]; u8 aptx[0x1]; - u8 reserved_4[0x6]; + u8 reserved_at_42[0x6]; u8 pfctx[0x8]; - u8 reserved_5[0x10]; + u8 reserved_at_50[0x10]; u8 pprx[0x1]; u8 aprx[0x1]; - u8 reserved_6[0x6]; + u8 reserved_at_62[0x6]; u8 pfcrx[0x8]; - u8 reserved_7[0x10]; + u8 reserved_at_70[0x10]; - u8 reserved_8[0x80]; + u8 reserved_at_80[0x80]; }; struct mlx5_ifc_pelc_reg_bits { u8 op[0x4]; - u8 reserved_0[0x4]; + u8 reserved_at_4[0x4]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 op_admin[0x8]; u8 op_capability[0x8]; @@ -6634,28 +6634,28 @@ struct mlx5_ifc_pelc_reg_bits { u8 active[0x40]; - u8 reserved_2[0x80]; + u8 reserved_at_140[0x80]; }; struct mlx5_ifc_peir_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_2[0xc]; + u8 reserved_at_20[0xc]; u8 error_count[0x4]; - u8 reserved_3[0x10]; + u8 reserved_at_30[0x10]; - u8 reserved_4[0xc]; + u8 reserved_at_40[0xc]; u8 lane[0x4]; - u8 reserved_5[0x8]; + u8 reserved_at_50[0x8]; u8 error_type[0x8]; }; struct mlx5_ifc_pcap_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 local_port[0x8]; - u8 reserved_1[0x10]; + u8 reserved_at_10[0x10]; u8 port_capability_mask[4][0x20]; }; @@ -6663,46 +6663,46 @@ struct mlx5_ifc_pcap_reg_bits { struct mlx5_ifc_paos_reg_bits { u8 swid[0x8]; u8 local_port[0x8]; - u8 reserved_0[0x4]; + u8 reserved_at_10[0x4]; u8 admin_status[0x4]; - u8 reserved_1[0x4]; + u8 reserved_at_18[0x4]; u8 oper_status[0x4]; u8 ase[0x1]; u8 ee[0x1]; - u8 reserved_2[0x1c]; + u8 reserved_at_22[0x1c]; u8 e[0x2]; - u8 reserved_3[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_pamp_reg_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 opamp_group[0x8]; - u8 reserved_1[0xc]; + u8 reserved_at_10[0xc]; u8 opamp_group_type[0x4]; u8 start_index[0x10]; - u8 reserved_2[0x4]; + u8 reserved_at_30[0x4]; u8 num_of_indices[0xc]; u8 index_data[18][0x10]; }; struct mlx5_ifc_lane_2_module_mapping_bits { - u8 reserved_0[0x6]; + u8 reserved_at_0[0x6]; u8 rx_lane[0x2]; - u8 reserved_1[0x6]; + u8 reserved_at_8[0x6]; u8 tx_lane[0x2]; - u8 reserved_2[0x8]; + u8 reserved_at_10[0x8]; u8 module[0x8]; }; struct mlx5_ifc_bufferx_reg_bits { - u8 reserved_0[0x6]; + u8 reserved_at_0[0x6]; u8 lossy[0x1]; u8 epsb[0x1]; - u8 reserved_1[0xc]; + u8 reserved_at_8[0xc]; u8 size[0xc]; u8 xoff_threshold[0x10]; @@ -6714,21 +6714,21 @@ struct mlx5_ifc_set_node_in_bits { }; struct mlx5_ifc_register_power_settings_bits { - u8 reserved_0[0x18]; + u8 reserved_at_0[0x18]; u8 power_settings_level[0x8]; - u8 reserved_1[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_register_host_endianness_bits { u8 he[0x1]; - u8 reserved_0[0x1f]; + u8 reserved_at_1[0x1f]; - u8 reserved_1[0x60]; + u8 reserved_at_20[0x60]; }; struct mlx5_ifc_umr_pointer_desc_argument_bits { - u8 reserved_0[0x20]; + u8 reserved_at_0[0x20]; u8 mkey[0x20]; @@ -6741,7 +6741,7 @@ struct mlx5_ifc_ud_adrs_vector_bits { u8 dc_key[0x40]; u8 ext[0x1]; - u8 reserved_0[0x7]; + u8 reserved_at_41[0x7]; u8 destination_qp_dct[0x18]; u8 static_rate[0x4]; @@ -6750,7 +6750,7 @@ struct mlx5_ifc_ud_adrs_vector_bits { u8 mlid[0x7]; u8 rlid_udp_sport[0x10]; - u8 reserved_1[0x20]; + u8 reserved_at_80[0x20]; u8 rmac_47_16[0x20]; @@ -6758,9 +6758,9 @@ struct mlx5_ifc_ud_adrs_vector_bits { u8 tclass[0x8]; u8 hop_limit[0x8]; - u8 reserved_2[0x1]; + u8 reserved_at_e0[0x1]; u8 grh[0x1]; - u8 reserved_3[0x2]; + u8 reserved_at_e2[0x2]; u8 src_addr_index[0x8]; u8 flow_label[0x14]; @@ -6768,27 +6768,27 @@ struct mlx5_ifc_ud_adrs_vector_bits { }; struct mlx5_ifc_pages_req_event_bits { - u8 reserved_0[0x10]; + u8 reserved_at_0[0x10]; u8 function_id[0x10]; u8 num_pages[0x20]; - u8 reserved_1[0xa0]; + u8 reserved_at_40[0xa0]; }; struct mlx5_ifc_eqe_bits { - u8 reserved_0[0x8]; + u8 reserved_at_0[0x8]; u8 event_type[0x8]; - u8 reserved_1[0x8]; + u8 reserved_at_10[0x8]; u8 event_sub_type[0x8]; - u8 reserved_2[0xe0]; + u8 reserved_at_20[0xe0]; union mlx5_ifc_event_auto_bits event_data; - u8 reserved_3[0x10]; + u8 reserved_at_1e0[0x10]; u8 signature[0x8]; - u8 reserved_4[0x7]; + u8 reserved_at_1f8[0x7]; u8 owner[0x1]; }; @@ -6798,14 +6798,14 @@ enum { struct mlx5_ifc_cmd_queue_entry_bits { u8 type[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 input_length[0x20]; u8 input_mailbox_pointer_63_32[0x20]; u8 input_mailbox_pointer_31_9[0x17]; - u8 reserved_1[0x9]; + u8 reserved_at_77[0x9]; u8 command_input_inline_data[16][0x8]; @@ -6814,20 +6814,20 @@ struct mlx5_ifc_cmd_queue_entry_bits { u8 output_mailbox_pointer_63_32[0x20]; u8 output_mailbox_pointer_31_9[0x17]; - u8 reserved_2[0x9]; + u8 reserved_at_1b7[0x9]; u8 output_length[0x20]; u8 token[0x8]; u8 signature[0x8]; - u8 reserved_3[0x8]; + u8 reserved_at_1f0[0x8]; u8 status[0x7]; u8 ownership[0x1]; }; struct mlx5_ifc_cmd_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; @@ -6836,9 +6836,9 @@ struct mlx5_ifc_cmd_out_bits { struct mlx5_ifc_cmd_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; u8 command[0][0x20]; @@ -6847,16 +6847,16 @@ struct mlx5_ifc_cmd_in_bits { struct mlx5_ifc_cmd_if_box_bits { u8 mailbox_data[512][0x8]; - u8 reserved_0[0x180]; + u8 reserved_at_1000[0x180]; u8 next_pointer_63_32[0x20]; u8 next_pointer_31_10[0x16]; - u8 reserved_1[0xa]; + u8 reserved_at_11b6[0xa]; u8 block_number[0x20]; - u8 reserved_2[0x8]; + u8 reserved_at_11e0[0x8]; u8 token[0x8]; u8 ctrl_signature[0x8]; u8 signature[0x8]; @@ -6866,7 +6866,7 @@ struct mlx5_ifc_mtt_bits { u8 ptag_63_32[0x20]; u8 ptag_31_8[0x18]; - u8 reserved_0[0x6]; + u8 reserved_at_38[0x6]; u8 wr_en[0x1]; u8 rd_en[0x1]; }; @@ -6904,38 +6904,38 @@ struct mlx5_ifc_initial_seg_bits { u8 cmd_interface_rev[0x10]; u8 fw_rev_subminor[0x10]; - u8 reserved_0[0x40]; + u8 reserved_at_40[0x40]; u8 cmdq_phy_addr_63_32[0x20]; u8 cmdq_phy_addr_31_12[0x14]; - u8 reserved_1[0x2]; + u8 reserved_at_b4[0x2]; u8 nic_interface[0x2]; u8 log_cmdq_size[0x4]; u8 log_cmdq_stride[0x4]; u8 command_doorbell_vector[0x20]; - u8 reserved_2[0xf00]; + u8 reserved_at_e0[0xf00]; u8 initializing[0x1]; - u8 reserved_3[0x4]; + u8 reserved_at_fe1[0x4]; u8 nic_interface_supported[0x3]; - u8 reserved_4[0x18]; + u8 reserved_at_fe8[0x18]; struct mlx5_ifc_health_buffer_bits health_buffer; u8 no_dram_nic_offset[0x20]; - u8 reserved_5[0x6e40]; + u8 reserved_at_1220[0x6e40]; - u8 reserved_6[0x1f]; + u8 reserved_at_8060[0x1f]; u8 clear_int[0x1]; u8 health_syndrome[0x8]; u8 health_counter[0x18]; - u8 reserved_7[0x17fc0]; + u8 reserved_at_80a0[0x17fc0]; }; union mlx5_ifc_ports_control_registers_document_bits { @@ -6980,44 +6980,44 @@ union mlx5_ifc_ports_control_registers_document_bits { struct mlx5_ifc_pvlc_reg_bits pvlc_reg; struct mlx5_ifc_slrg_reg_bits slrg_reg; struct mlx5_ifc_sltp_reg_bits sltp_reg; - u8 reserved_0[0x60e0]; + u8 reserved_at_0[0x60e0]; }; union mlx5_ifc_debug_enhancements_document_bits { struct mlx5_ifc_health_buffer_bits health_buffer; - u8 reserved_0[0x200]; + u8 reserved_at_0[0x200]; }; union mlx5_ifc_uplink_pci_interface_document_bits { struct mlx5_ifc_initial_seg_bits initial_seg; - u8 reserved_0[0x20060]; + u8 reserved_at_0[0x20060]; }; struct mlx5_ifc_set_flow_table_root_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_set_flow_table_root_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x40]; + u8 reserved_at_40[0x40]; u8 table_type[0x8]; - u8 reserved_3[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_4[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_5[0x140]; + u8 reserved_at_c0[0x140]; }; enum { @@ -7026,39 +7026,39 @@ enum { struct mlx5_ifc_modify_flow_table_out_bits { u8 status[0x8]; - u8 reserved_0[0x18]; + u8 reserved_at_8[0x18]; u8 syndrome[0x20]; - u8 reserved_1[0x40]; + u8 reserved_at_40[0x40]; }; struct mlx5_ifc_modify_flow_table_in_bits { u8 opcode[0x10]; - u8 reserved_0[0x10]; + u8 reserved_at_10[0x10]; - u8 reserved_1[0x10]; + u8 reserved_at_20[0x10]; u8 op_mod[0x10]; - u8 reserved_2[0x20]; + u8 reserved_at_40[0x20]; - u8 reserved_3[0x10]; + u8 reserved_at_60[0x10]; u8 modify_field_select[0x10]; u8 table_type[0x8]; - u8 reserved_4[0x18]; + u8 reserved_at_88[0x18]; - u8 reserved_5[0x8]; + u8 reserved_at_a0[0x8]; u8 table_id[0x18]; - u8 reserved_6[0x4]; + u8 reserved_at_c0[0x4]; u8 table_miss_mode[0x4]; - u8 reserved_7[0x18]; + u8 reserved_at_c8[0x18]; - u8 reserved_8[0x8]; + u8 reserved_at_e0[0x8]; u8 table_miss_id[0x18]; - u8 reserved_9[0x100]; + u8 reserved_at_100[0x100]; }; #endif /* MLX5_IFC_H */ From b236872739df6410c7c60874ff8f3fb188ffb9d0 Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 9 Feb 2016 14:57:43 +0200 Subject: [PATCH 202/489] net/mlx5e: Remove select queue ndo initialization Currently mlx5e_select_queue is redundant since num_tc is always 1. Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 6a3e430f1062..bca6e85e1c8e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2137,9 +2137,6 @@ static void mlx5e_build_netdev(struct net_device *netdev) SET_NETDEV_DEV(netdev, &mdev->pdev->dev); - if (priv->params.num_tc > 1) - mlx5e_netdev_ops.ndo_select_queue = mlx5e_select_queue; - if (MLX5_CAP_GEN(mdev, vport_group_manager)) { mlx5e_netdev_ops.ndo_set_vf_mac = mlx5e_set_vf_mac; mlx5e_netdev_ops.ndo_set_vf_vlan = mlx5e_set_vf_vlan; From b0eed40ea15235b1dd138093901569077ba532ee Mon Sep 17 00:00:00 2001 From: Saeed Mahameed Date: Tue, 9 Feb 2016 14:57:44 +0200 Subject: [PATCH 203/489] net/mlx5e: Use static constant netdevice ndos Currently our netdevice ops is a one static global variable which is referenced by all mlx5e netdevice instances. This can be problematic when different driver instances do not share same HW capabilities (e.g SRIOV PF and VFs probed to the host). Now we have two constant global netdevice ops variables, one for basic netdevice ops and the other with extended SRIOV ops, on netdevice construction we choose the one suitable for current device capabilities. Fixes: 66e49dedada6 ("net/mlx5e: Add support for SR-IOV ndos") Signed-off-by: Saeed Mahameed Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 41 +++++++++++++------ 1 file changed, 28 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index bca6e85e1c8e..d4e1c3045200 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -2024,18 +2024,37 @@ static int mlx5e_get_vf_stats(struct net_device *dev, vf_stats); } -static struct net_device_ops mlx5e_netdev_ops = { +static const struct net_device_ops mlx5e_netdev_ops_basic = { .ndo_open = mlx5e_open, .ndo_stop = mlx5e_close, .ndo_start_xmit = mlx5e_xmit, .ndo_get_stats64 = mlx5e_get_stats, .ndo_set_rx_mode = mlx5e_set_rx_mode, .ndo_set_mac_address = mlx5e_set_mac, - .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, + .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, .ndo_set_features = mlx5e_set_features, - .ndo_change_mtu = mlx5e_change_mtu, - .ndo_do_ioctl = mlx5e_ioctl, + .ndo_change_mtu = mlx5e_change_mtu, + .ndo_do_ioctl = mlx5e_ioctl, +}; + +static const struct net_device_ops mlx5e_netdev_ops_sriov = { + .ndo_open = mlx5e_open, + .ndo_stop = mlx5e_close, + .ndo_start_xmit = mlx5e_xmit, + .ndo_get_stats64 = mlx5e_get_stats, + .ndo_set_rx_mode = mlx5e_set_rx_mode, + .ndo_set_mac_address = mlx5e_set_mac, + .ndo_vlan_rx_add_vid = mlx5e_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = mlx5e_vlan_rx_kill_vid, + .ndo_set_features = mlx5e_set_features, + .ndo_change_mtu = mlx5e_change_mtu, + .ndo_do_ioctl = mlx5e_ioctl, + .ndo_set_vf_mac = mlx5e_set_vf_mac, + .ndo_set_vf_vlan = mlx5e_set_vf_vlan, + .ndo_get_vf_config = mlx5e_get_vf_config, + .ndo_set_vf_link_state = mlx5e_set_vf_link_state, + .ndo_get_vf_stats = mlx5e_get_vf_stats, }; static int mlx5e_check_required_hca_cap(struct mlx5_core_dev *mdev) @@ -2137,15 +2156,11 @@ static void mlx5e_build_netdev(struct net_device *netdev) SET_NETDEV_DEV(netdev, &mdev->pdev->dev); - if (MLX5_CAP_GEN(mdev, vport_group_manager)) { - mlx5e_netdev_ops.ndo_set_vf_mac = mlx5e_set_vf_mac; - mlx5e_netdev_ops.ndo_set_vf_vlan = mlx5e_set_vf_vlan; - mlx5e_netdev_ops.ndo_get_vf_config = mlx5e_get_vf_config; - mlx5e_netdev_ops.ndo_set_vf_link_state = mlx5e_set_vf_link_state; - mlx5e_netdev_ops.ndo_get_vf_stats = mlx5e_get_vf_stats; - } + if (MLX5_CAP_GEN(mdev, vport_group_manager)) + netdev->netdev_ops = &mlx5e_netdev_ops_sriov; + else + netdev->netdev_ops = &mlx5e_netdev_ops_basic; - netdev->netdev_ops = &mlx5e_netdev_ops; netdev->watchdog_timeo = 15 * HZ; netdev->ethtool_ops = &mlx5e_ethtool_ops; From 78565208d73ca9b654fb9a6b142214d52eeedfd1 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 9 Feb 2016 06:14:43 -0800 Subject: [PATCH 204/489] net: Copy inner L3 and L4 headers as unaligned on GRE TEB This patch corrects the unaligned accesses seen on GRE TEB tunnels when generating hash keys. Specifically what this patch does is make it so that we force the use of skb_copy_bits when the GRE inner headers will be unaligned due to NET_IP_ALIGNED being a non-zero value. Signed-off-by: Alexander Duyck Acked-by: Tom Herbert Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index eab81bc80e5c..12e700332010 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -399,6 +399,13 @@ ip_proto_again: goto out_bad; proto = eth->h_proto; nhoff += sizeof(*eth); + + /* Cap headers that we access via pointers at the + * end of the Ethernet header as our maximum alignment + * at that point is only 2 bytes. + */ + if (NET_IP_ALIGN) + hlen = nhoff; } key_control->flags |= FLOW_DIS_ENCAPSULATION; From c278c253f3d992c6994d08aa0efb2b6806ca396f Mon Sep 17 00:00:00 2001 From: Alexander Kochetkov Date: Tue, 9 Feb 2016 18:20:38 +0300 Subject: [PATCH 205/489] net: arc_emac: fix koops caused by sk_buff free There is a race between arc_emac_tx() and arc_emac_tx_clean(). sk_buff got freed by arc_emac_tx_clean() while arc_emac_tx() submitting sk_buff. In order to free sk_buff arc_emac_tx_clean() checks: if ((info & FOR_EMAC) || !txbd->data) break; ... dev_kfree_skb_irq(skb); If condition false, arc_emac_tx_clean() free sk_buff. In order to submit txbd, arc_emac_tx() do: priv->tx_buff[*txbd_curr].skb = skb; ... priv->txbd[*txbd_curr].data = cpu_to_le32(addr); ... ... <== arc_emac_tx_clean() check condition here ... <== (info & FOR_EMAC) is false ... <== !txbd->data is false ... *info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len); In order to reproduce the situation, run device: # iperf -s run on host: # iperf -t 600 -c [ 28.396284] ------------[ cut here ]------------ [ 28.400912] kernel BUG at .../net/core/skbuff.c:1355! [ 28.414019] Internal error: Oops - BUG: 0 [#1] SMP ARM [ 28.419150] Modules linked in: [ 28.422219] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G B 4.4.0+ #120 [ 28.429516] Hardware name: Rockchip (Device Tree) [ 28.434216] task: c0665070 ti: c0660000 task.ti: c0660000 [ 28.439622] PC is at skb_put+0x10/0x54 [ 28.443381] LR is at arc_emac_poll+0x260/0x474 [ 28.447821] pc : [] lr : [] psr: a0070113 [ 28.447821] sp : c0661e58 ip : eea68502 fp : ef377000 [ 28.459280] r10: 0000012c r9 : f08b2000 r8 : eeb57100 [ 28.464498] r7 : 00000000 r6 : ef376594 r5 : 00000077 r4 : ef376000 [ 28.471015] r3 : 0030488b r2 : ef13e880 r1 : 000005ee r0 : eeb57100 [ 28.477534] Flags: NzCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none [ 28.484658] Control: 10c5387d Table: 8eaf004a DAC: 00000051 [ 28.490396] Process swapper/0 (pid: 0, stack limit = 0xc0660210) [ 28.496393] Stack: (0xc0661e58 to 0xc0662000) [ 28.500745] 1e40: 00000002 00000000 [ 28.508913] 1e60: 00000000 ef376520 00000028 f08b23b8 00000000 ef376520 ef7b6900 c028fc64 [ 28.517082] 1e80: 2f158000 c0661ea8 c0661eb0 0000012c c065e900 c03bdeac ffff95e9 c0662100 [ 28.525250] 1ea0: c0663924 00000028 c0661ea8 c0661ea8 c0661eb0 c0661eb0 0000001e c0660000 [ 28.533417] 1ec0: 40000003 00000008 c0695a00 0000000a c066208c 00000100 c0661ee0 c0027410 [ 28.541584] 1ee0: ef0fb700 2f158000 00200000 ffff95e8 00000004 c0662100 c0662080 00000003 [ 28.549751] 1f00: 00000000 00000000 00000000 c065b45c 0000001e ef005000 c0647a30 00000000 [ 28.557919] 1f20: 00000000 c0027798 00000000 c005cf40 f0802100 c0662ffc c0661f60 f0803100 [ 28.566088] 1f40: c0661fb8 c00093bc c000ffb4 60070013 ffffffff c0661f94 c0661fb8 c00137d4 [ 28.574267] 1f60: 00000001 00000000 00000000 c001ffa0 00000000 c0660000 00000000 c065a364 [ 28.582441] 1f80: c0661fb8 c0647a30 00000000 00000000 00000000 c0661fb0 c000ffb0 c000ffb4 [ 28.590608] 1fa0: 60070013 ffffffff 00000051 00000000 00000000 c005496c c0662400 c061bc40 [ 28.598776] 1fc0: ffffffff ffffffff 00000000 c061b680 00000000 c0647a30 00000000 c0695294 [ 28.606943] 1fe0: c0662488 c0647a2c c066619c 6000406a 413fc090 6000807c 00000000 00000000 [ 28.615127] [] (skb_put) from [] (0xef376520) [ 28.621218] Code: e5902054 e590c090 e3520000 0a000000 (e7f001f2) [ 28.627307] ---[ end trace 4824734e2243fdb6 ]--- [ 34.377068] Internal error: Oops: 17 [#1] SMP ARM [ 34.382854] Modules linked in: [ 34.385947] CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 4.4.0+ #120 [ 34.392219] Hardware name: Rockchip (Device Tree) [ 34.396937] task: ef02d040 ti: ef05c000 task.ti: ef05c000 [ 34.402376] PC is at __dev_kfree_skb_irq+0x4/0x80 [ 34.407121] LR is at arc_emac_poll+0x130/0x474 [ 34.411583] pc : [] lr : [] psr: 60030013 [ 34.411583] sp : ef05de68 ip : 0008e83c fp : ef377000 [ 34.423062] r10: c001bec4 r9 : 00000000 r8 : f08b24c8 [ 34.428296] r7 : f08b2400 r6 : 00000075 r5 : 00000019 r4 : ef376000 [ 34.434827] r3 : 00060000 r2 : 00000042 r1 : 00000001 r0 : 00000000 [ 34.441365] Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment none [ 34.448507] Control: 10c5387d Table: 8f25c04a DAC: 00000051 [ 34.454262] Process ksoftirqd/0 (pid: 3, stack limit = 0xef05c210) [ 34.460449] Stack: (0xef05de68 to 0xef05e000) [ 34.464827] de60: ef376000 c028fd94 00000000 c0669480 c0669480 ef376520 [ 34.473022] de80: 00000028 00000001 00002ae4 ef376520 ef7b6900 c028fc64 2f158000 ef05dec0 [ 34.481215] dea0: ef05dec8 0000012c c065e900 c03bdeac ffff983f c0662100 c0663924 00000028 [ 34.489409] dec0: ef05dec0 ef05dec0 ef05dec8 ef05dec8 ef7b6000 ef05c000 40000003 00000008 [ 34.497600] dee0: c0695a00 0000000a c066208c 00000100 ef05def8 c0027410 ef7b6000 40000000 [ 34.505795] df00: 04208040 ffff983e 00000004 c0662100 c0662080 00000003 ef05c000 ef027340 [ 34.513985] df20: ef05c000 c0666c2c 00000000 00000001 00000002 00000000 00000000 c0027568 [ 34.522176] df40: ef027340 c003ef48 ef027300 00000000 ef027340 c003edd4 00000000 00000000 [ 34.530367] df60: 00000000 c003c37c ffffff7f 00000001 00000000 ef027340 00000000 00030003 [ 34.538559] df80: ef05df80 ef05df80 00000000 00000000 ef05df90 ef05df90 ef05dfac ef027300 [ 34.546750] dfa0: c003c2a4 00000000 00000000 c000f578 00000000 00000000 00000000 00000000 [ 34.554939] dfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 [ 34.563129] dfe0: 00000000 00000000 00000000 00000000 00000013 00000000 ffffffff dfff7fff [ 34.571360] [] (__dev_kfree_skb_irq) from [] (arc_emac_poll+0x130/0x474) [ 34.579840] [] (arc_emac_poll) from [] (net_rx_action+0xdc/0x28c) [ 34.587712] [] (net_rx_action) from [] (__do_softirq+0xcc/0x1f8) [ 34.595482] [] (__do_softirq) from [] (run_ksoftirqd+0x2c/0x50) [ 34.603168] [] (run_ksoftirqd) from [] (smpboot_thread_fn+0x174/0x18c) [ 34.611466] [] (smpboot_thread_fn) from [] (kthread+0xd8/0xec) [ 34.619075] [] (kthread) from [] (ret_from_fork+0x14/0x3c) [ 34.626317] Code: e8bd8010 e3a00000 e12fff1e e92d4010 (e59030a4) [ 34.632572] ---[ end trace cca5a3d86a82249a ]--- Signed-off-by: Alexander Kochetkov Signed-off-by: David S. Miller --- drivers/net/ethernet/arc/emac_main.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index abe1eabc0171..63a63e31d59d 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -163,7 +163,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) struct sk_buff *skb = tx_buff->skb; unsigned int info = le32_to_cpu(txbd->info); - if ((info & FOR_EMAC) || !txbd->data) + if ((info & FOR_EMAC) || !txbd->data || !skb) break; if (unlikely(info & (DROP | DEFR | LTCL | UFLO))) { @@ -191,6 +191,7 @@ static void arc_emac_tx_clean(struct net_device *ndev) txbd->data = 0; txbd->info = 0; + tx_buff->skb = NULL; *txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM; } @@ -610,7 +611,6 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev) dma_unmap_addr_set(&priv->tx_buff[*txbd_curr], addr, addr); dma_unmap_len_set(&priv->tx_buff[*txbd_curr], len, len); - priv->tx_buff[*txbd_curr].skb = skb; priv->txbd[*txbd_curr].data = cpu_to_le32(addr); /* Make sure pointer to data buffer is set */ @@ -620,6 +620,11 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev) *info = cpu_to_le32(FOR_EMAC | FIRST_OR_LAST_MASK | len); + /* Make sure info word is set */ + wmb(); + + priv->tx_buff[*txbd_curr].skb = skb; + /* Increment index to point to the next BD */ *txbd_curr = (*txbd_curr + 1) % TX_BD_NUM; From 99f93a156a2aa9ac1e44f7cb1a197425e6d9879a Mon Sep 17 00:00:00 2001 From: Alexander Kochetkov Date: Tue, 9 Feb 2016 18:20:39 +0300 Subject: [PATCH 206/489] net: arc_emac: reset txbd_curr and txbd_dirty pointers to zero EMAC reset internal tx ring pointer to zero at statup. txbd_curr and txbd_dirty can be different from zero. That cause ethernet transfer hang (no packets transmitted). In order to reproduce, run on device: ifconfig eth0 down ifconfig eth0 up Signed-off-by: Alexander Kochetkov Signed-off-by: David S. Miller --- drivers/net/ethernet/arc/emac_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 63a63e31d59d..4f6e5be184df 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -447,6 +447,9 @@ static int arc_emac_open(struct net_device *ndev) *last_rx_bd = (*last_rx_bd + 1) % RX_BD_NUM; } + priv->txbd_curr = 0; + priv->txbd_dirty = 0; + /* Clean Tx BD's */ memset(priv->txbd, 0, TX_RING_SZ); From b530b16413b7f99977ded50a3c4bebd2ea79c41b Mon Sep 17 00:00:00 2001 From: Alexander Kochetkov Date: Tue, 9 Feb 2016 18:20:40 +0300 Subject: [PATCH 207/489] net: arc_emac: fix sk_buff leak EMAC could be disabled, while there is some sb_buff in use. That buffers got lost for linux. In order to reproduce run on device during active ethernet work: ifconfig eth0 down Signed-off-by: Alexander Kochetkov Signed-off-by: David S. Miller --- drivers/net/ethernet/arc/emac_main.c | 62 ++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c index 4f6e5be184df..6446af1403f7 100644 --- a/drivers/net/ethernet/arc/emac_main.c +++ b/drivers/net/ethernet/arc/emac_main.c @@ -517,6 +517,64 @@ static void arc_emac_set_rx_mode(struct net_device *ndev) } } +/** + * arc_free_tx_queue - free skb from tx queue + * @ndev: Pointer to the network device. + * + * This function must be called while EMAC disable + */ +static void arc_free_tx_queue(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + unsigned int i; + + for (i = 0; i < TX_BD_NUM; i++) { + struct arc_emac_bd *txbd = &priv->txbd[i]; + struct buffer_state *tx_buff = &priv->tx_buff[i]; + + if (tx_buff->skb) { + dma_unmap_single(&ndev->dev, dma_unmap_addr(tx_buff, addr), + dma_unmap_len(tx_buff, len), DMA_TO_DEVICE); + + /* return the sk_buff to system */ + dev_kfree_skb_irq(tx_buff->skb); + } + + txbd->info = 0; + txbd->data = 0; + tx_buff->skb = NULL; + } +} + +/** + * arc_free_rx_queue - free skb from rx queue + * @ndev: Pointer to the network device. + * + * This function must be called while EMAC disable + */ +static void arc_free_rx_queue(struct net_device *ndev) +{ + struct arc_emac_priv *priv = netdev_priv(ndev); + unsigned int i; + + for (i = 0; i < RX_BD_NUM; i++) { + struct arc_emac_bd *rxbd = &priv->rxbd[i]; + struct buffer_state *rx_buff = &priv->rx_buff[i]; + + if (rx_buff->skb) { + dma_unmap_single(&ndev->dev, dma_unmap_addr(rx_buff, addr), + dma_unmap_len(rx_buff, len), DMA_FROM_DEVICE); + + /* return the sk_buff to system */ + dev_kfree_skb_irq(rx_buff->skb); + } + + rxbd->info = 0; + rxbd->data = 0; + rx_buff->skb = NULL; + } +} + /** * arc_emac_stop - Close the network device. * @ndev: Pointer to the network device. @@ -538,6 +596,10 @@ static int arc_emac_stop(struct net_device *ndev) /* Disable EMAC */ arc_reg_clr(priv, R_CTRL, EN_MASK); + /* Return the sk_buff to system */ + arc_free_tx_queue(ndev); + arc_free_rx_queue(ndev); + return 0; } From b5e4d0bcf77e56362252a7ced4dbb476425e1655 Mon Sep 17 00:00:00 2001 From: Hariprasad Shenai Date: Wed, 10 Feb 2016 12:28:49 +0530 Subject: [PATCH 208/489] cxgb4: Add pci device id for chelsio t540 lom adapter Signed-off-by: Hariprasad Shenai Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index a8dda635456d..06bc2d2e7a73 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -165,6 +165,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x5098), /* Custom 2x40G QSFP */ CH_PCI_ID_TABLE_FENTRY(0x5099), /* Custom 2x40G QSFP */ CH_PCI_ID_TABLE_FENTRY(0x509a), /* Custom T520-CR */ + CH_PCI_ID_TABLE_FENTRY(0x509b), /* Custom T540-CR LOM */ /* T6 adapters: */ From 56bb7fd994f4cc163de08006bf68d959027a9f36 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 10 Feb 2016 16:09:02 +0100 Subject: [PATCH 209/489] bridge: mdb: avoid uninitialized variable warning A recent change to the mdb code confused the compiler to the point where it did not realize that the port-group returned from br_mdb_add_group() is always valid when the function returns a nonzero return value, so we get a spurious warning: net/bridge/br_mdb.c: In function 'br_mdb_add': net/bridge/br_mdb.c:542:4: error: 'pg' may be used uninitialized in this function [-Werror=maybe-uninitialized] __br_mdb_notify(dev, entry, RTM_NEWMDB, pg); Slightly rearranging the code in br_mdb_add_group() makes the problem go away, as gcc is clever enough to see that both functions check for 'ret != 0'. Signed-off-by: Arnd Bergmann Fixes: 9e8430f8d60d ("bridge: mdb: Passing the port-group pointer to br_mdb module") Signed-off-by: David S. Miller --- net/bridge/br_mdb.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 30e105f57f0d..74c278e00225 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -425,8 +425,8 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port, mp = br_mdb_ip_get(mdb, group); if (!mp) { mp = br_multicast_new_group(br, port, group); - err = PTR_ERR(mp); - if (IS_ERR(mp)) + err = PTR_ERR_OR_ZERO(mp); + if (err) return err; } From b763499ee16b74707af0fb26ab0a26bd9719870b Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 10 Feb 2016 17:33:46 -0500 Subject: [PATCH 210/489] bnxt_en: Fix ethtool autoneg logic. 1. Determine autoneg on|off setting from link_info->autoneg. Using the firmware returned setting can be misleading if autoneg is changed and there hasn't been a phy update from the firmware. 2. If autoneg is disabled, link_info->autoneg should be set to 0 to indicate both speed and flow control autoneg are disabled. 3. To enable autoneg flow control, speed autoneg must be enabled. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 922b898e7a32..724030785e8b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -561,7 +561,7 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) if (link_info->auto_link_speeds) cmd->supported |= SUPPORTED_Autoneg; - if (BNXT_AUTO_MODE(link_info->auto_mode)) { + if (link_info->autoneg) { cmd->advertising = bnxt_fw_to_ethtool_advertised_spds(link_info); cmd->advertising |= ADVERTISED_Autoneg; @@ -729,7 +729,7 @@ static int bnxt_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) speed = ethtool_cmd_speed(cmd); link_info->req_link_speed = bnxt_get_fw_speed(dev, speed); link_info->req_duplex = BNXT_LINK_DUPLEX_FULL; - link_info->autoneg &= ~BNXT_AUTONEG_SPEED; + link_info->autoneg = 0; link_info->advertising = 0; } @@ -748,8 +748,7 @@ static void bnxt_get_pauseparam(struct net_device *dev, if (BNXT_VF(bp)) return; - epause->autoneg = !!(link_info->auto_pause_setting & - BNXT_LINK_PAUSE_BOTH); + epause->autoneg = !!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL); epause->rx_pause = ((link_info->pause & BNXT_LINK_PAUSE_RX) != 0); epause->tx_pause = ((link_info->pause & BNXT_LINK_PAUSE_TX) != 0); } @@ -765,6 +764,9 @@ static int bnxt_set_pauseparam(struct net_device *dev, return rc; if (epause->autoneg) { + if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) + return -EINVAL; + link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL; link_info->req_flow_ctrl |= BNXT_LINK_PAUSE_BOTH; } else { From 0d8abf020199b0cbc5fb3aa309d36f0ac1b91631 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 10 Feb 2016 17:33:47 -0500 Subject: [PATCH 211/489] bnxt_en: Cleanup and Fix flow control setup logic Cleanup bnxt_probe_phy() to cleanly separate 2 code blocks for autoneg on and off. Autoneg flow control is possible only if autoneg is enabled. In bnxt_get_settings(), Pause and Asym_Pause are always supported. Only the advertisement bits change depending on the ethtool -A setting in auto mode. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 20 +++++++------------ .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 15 ++------------ 2 files changed, 9 insertions(+), 26 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 5dc89e527e7d..ddcf7efbee9e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -5670,22 +5670,16 @@ static int bnxt_probe_phy(struct bnxt *bp) } /*initialize the ethool setting copy with NVM settings */ - if (BNXT_AUTO_MODE(link_info->auto_mode)) - link_info->autoneg |= BNXT_AUTONEG_SPEED; - - if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) { - if (link_info->auto_pause_setting == BNXT_LINK_PAUSE_BOTH) - link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL; + if (BNXT_AUTO_MODE(link_info->auto_mode)) { + link_info->autoneg = BNXT_AUTONEG_SPEED | + BNXT_AUTONEG_FLOW_CTRL; + link_info->advertising = link_info->auto_link_speeds; link_info->req_flow_ctrl = link_info->auto_pause_setting; - } else if (link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) { + } else { + link_info->req_link_speed = link_info->force_link_speed; + link_info->req_duplex = link_info->duplex_setting; link_info->req_flow_ctrl = link_info->force_pause_setting; } - link_info->req_duplex = link_info->duplex_setting; - if (link_info->autoneg & BNXT_AUTONEG_SPEED) - link_info->req_link_speed = link_info->auto_link_speed; - else - link_info->req_link_speed = link_info->force_link_speed; - link_info->advertising = link_info->auto_link_speeds; snprintf(phy_ver, PHY_VER_STR_LEN, " ph %d.%d.%d", link_info->phy_ver[0], link_info->phy_ver[1], diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 724030785e8b..afc9655a4dac 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -557,6 +557,7 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) u16 ethtool_speed; cmd->supported = bnxt_fw_to_ethtool_support_spds(link_info); + cmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause; if (link_info->auto_link_speeds) cmd->supported |= SUPPORTED_Autoneg; @@ -570,28 +571,16 @@ static int bnxt_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) cmd->autoneg = AUTONEG_DISABLE; cmd->advertising = 0; } - if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) { + if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) { if ((link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) == BNXT_LINK_PAUSE_BOTH) { cmd->advertising |= ADVERTISED_Pause; - cmd->supported |= SUPPORTED_Pause; } else { cmd->advertising |= ADVERTISED_Asym_Pause; - cmd->supported |= SUPPORTED_Asym_Pause; if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_RX) cmd->advertising |= ADVERTISED_Pause; } - } else if (link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) { - if ((link_info->force_pause_setting & BNXT_LINK_PAUSE_BOTH) == - BNXT_LINK_PAUSE_BOTH) { - cmd->supported |= SUPPORTED_Pause; - } else { - cmd->supported |= SUPPORTED_Asym_Pause; - if (link_info->force_pause_setting & - BNXT_LINK_PAUSE_RX) - cmd->supported |= SUPPORTED_Pause; - } } cmd->port = PORT_NONE; From 1c49c421f3ec446f1e0eda6d965a6cb23214d7a1 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 10 Feb 2016 17:33:48 -0500 Subject: [PATCH 212/489] bnxt_en: Remove 20G support and advertise only 40GbaseCR4. 20G is not supported by production hardware and only the 40GbaseCR4 standard is supported. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 21 +++++-------------- 1 file changed, 5 insertions(+), 16 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index afc9655a4dac..3238817dfd5f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -486,15 +486,8 @@ static u32 bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info) speed_mask |= SUPPORTED_2500baseX_Full; if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB) speed_mask |= SUPPORTED_10000baseT_Full; - /* TODO: support 25GB, 50GB with different cable type */ - if (fw_speeds & BNXT_LINK_SPEED_MSK_20GB) - speed_mask |= SUPPORTED_20000baseMLD2_Full | - SUPPORTED_20000baseKR2_Full; if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB) - speed_mask |= SUPPORTED_40000baseKR4_Full | - SUPPORTED_40000baseCR4_Full | - SUPPORTED_40000baseSR4_Full | - SUPPORTED_40000baseLR4_Full; + speed_mask |= SUPPORTED_40000baseCR4_Full; return speed_mask; } @@ -514,15 +507,8 @@ static u32 bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info) speed_mask |= ADVERTISED_2500baseX_Full; if (fw_speeds & BNXT_LINK_SPEED_MSK_10GB) speed_mask |= ADVERTISED_10000baseT_Full; - /* TODO: how to advertise 20, 25, 40, 50GB with different cable type ?*/ - if (fw_speeds & BNXT_LINK_SPEED_MSK_20GB) - speed_mask |= ADVERTISED_20000baseMLD2_Full | - ADVERTISED_20000baseKR2_Full; if (fw_speeds & BNXT_LINK_SPEED_MSK_40GB) - speed_mask |= ADVERTISED_40000baseKR4_Full | - ADVERTISED_40000baseCR4_Full | - ADVERTISED_40000baseSR4_Full | - ADVERTISED_40000baseLR4_Full; + speed_mask |= ADVERTISED_40000baseCR4_Full; return speed_mask; } @@ -659,6 +645,9 @@ static u16 bnxt_get_fw_auto_link_speeds(u32 advertising) if (advertising & ADVERTISED_10000baseT_Full) fw_speed_mask |= BNXT_LINK_SPEED_MSK_10GB; + if (advertising & ADVERTISED_40000baseCR4_Full) + fw_speed_mask |= BNXT_LINK_SPEED_MSK_40GB; + return fw_speed_mask; } From 4419dbe6a0f031ddb2df4cd993805546a566d20e Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 10 Feb 2016 17:33:49 -0500 Subject: [PATCH 213/489] bnxt_en: Fix implementation of tx push operation. tx push is supported for small packets to reduce DMA latency. The following bugs are fixed in this patch: 1. Fix the definition of the push BD which is different from the DMA BD. 2. The push buffer has to be zero padded to the next 64-bit word boundary or tx checksum won't be correct. 3. Increase the tx push packet threshold to 164 bytes (192 bytes with the BD) so that small tunneled packets are within the threshold. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 42 ++++++++++++++--------- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 11 ++++-- 2 files changed, 34 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index ddcf7efbee9e..82f4e6d9ac7f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -69,7 +69,7 @@ MODULE_VERSION(DRV_MODULE_VERSION); #define BNXT_RX_DMA_OFFSET NET_SKB_PAD #define BNXT_RX_COPY_THRESH 256 -#define BNXT_TX_PUSH_THRESH 92 +#define BNXT_TX_PUSH_THRESH 164 enum board_idx { BCM57301, @@ -223,11 +223,12 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) } if (free_size == bp->tx_ring_size && length <= bp->tx_push_thresh) { - struct tx_push_bd *push = txr->tx_push; - struct tx_bd *tx_push = &push->txbd1; - struct tx_bd_ext *tx_push1 = &push->txbd2; - void *pdata = tx_push1 + 1; - int j; + struct tx_push_buffer *tx_push_buf = txr->tx_push; + struct tx_push_bd *tx_push = &tx_push_buf->push_bd; + struct tx_bd_ext *tx_push1 = &tx_push->txbd2; + void *pdata = tx_push_buf->data; + u64 *end; + int j, push_len; /* Set COAL_NOW to be ready quickly for the next push */ tx_push->tx_bd_len_flags_type = @@ -247,6 +248,9 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) tx_push1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); tx_push1->tx_bd_cfa_action = cpu_to_le32(cfa_action); + end = PTR_ALIGN(pdata + length + 1, 8) - 1; + *end = 0; + skb_copy_from_linear_data(skb, pdata, len); pdata += len; for (j = 0; j < last_frag; j++) { @@ -261,22 +265,29 @@ static netdev_tx_t bnxt_start_xmit(struct sk_buff *skb, struct net_device *dev) pdata += skb_frag_size(frag); } - memcpy(txbd, tx_push, sizeof(*txbd)); + txbd->tx_bd_len_flags_type = tx_push->tx_bd_len_flags_type; + txbd->tx_bd_haddr = txr->data_mapping; prod = NEXT_TX(prod); txbd = &txr->tx_desc_ring[TX_RING(prod)][TX_IDX(prod)]; memcpy(txbd, tx_push1, sizeof(*txbd)); prod = NEXT_TX(prod); - push->doorbell = + tx_push->doorbell = cpu_to_le32(DB_KEY_TX_PUSH | DB_LONG_TX_PUSH | prod); txr->tx_prod = prod; netdev_tx_sent_queue(txq, skb->len); - __iowrite64_copy(txr->tx_doorbell, push, - (length + sizeof(*push) + 8) / 8); + push_len = (length + sizeof(*tx_push) + 7) / 8; + if (push_len > 16) { + __iowrite64_copy(txr->tx_doorbell, tx_push_buf, 16); + __iowrite64_copy(txr->tx_doorbell + 4, tx_push_buf + 1, + push_len - 16); + } else { + __iowrite64_copy(txr->tx_doorbell, tx_push_buf, + push_len); + } tx_buf->is_push = 1; - goto tx_done; } @@ -1753,7 +1764,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) push_size = L1_CACHE_ALIGN(sizeof(struct tx_push_bd) + bp->tx_push_thresh); - if (push_size > 128) { + if (push_size > 256) { push_size = 0; bp->tx_push_thresh = 0; } @@ -1772,7 +1783,6 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) return rc; if (bp->tx_push_size) { - struct tx_bd *txbd; dma_addr_t mapping; /* One pre-allocated DMA buffer to backup @@ -1786,13 +1796,11 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) if (!txr->tx_push) return -ENOMEM; - txbd = &txr->tx_push->txbd1; - mapping = txr->tx_push_mapping + sizeof(struct tx_push_bd); - txbd->tx_bd_haddr = cpu_to_le64(mapping); + txr->data_mapping = cpu_to_le64(mapping); - memset(txbd + 1, 0, sizeof(struct tx_bd_ext)); + memset(txr->tx_push, 0, sizeof(struct tx_push_bd)); } ring->queue_id = bp->q_info[j].queue_id; if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 8af3ca8efcef..9b4866cefe4f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -523,10 +523,16 @@ struct bnxt_ring_struct { struct tx_push_bd { __le32 doorbell; - struct tx_bd txbd1; + __le32 tx_bd_len_flags_type; + u32 tx_bd_opaque; struct tx_bd_ext txbd2; }; +struct tx_push_buffer { + struct tx_push_bd push_bd; + u32 data[25]; +}; + struct bnxt_tx_ring_info { struct bnxt_napi *bnapi; u16 tx_prod; @@ -538,8 +544,9 @@ struct bnxt_tx_ring_info { dma_addr_t tx_desc_mapping[MAX_TX_PAGES]; - struct tx_push_bd *tx_push; + struct tx_push_buffer *tx_push; dma_addr_t tx_push_mapping; + __le64 data_mapping; #define BNXT_DEV_STATE_CLOSING 0x1 u32 dev_state; From 51dd55b5688e81f9f13fb520a59900d4c3959a9a Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Wed, 10 Feb 2016 17:33:50 -0500 Subject: [PATCH 214/489] bnxt_en: Reduce default ring sizes. The current default tx ring size of 512 causes an extra page to be allocated for the tx ring with only 1 entry in it. Reduce it to 511. The default rx ring size is also reduced to 511 to use less memory by default. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9b4866cefe4f..2be51b332652 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -411,8 +411,8 @@ struct rx_tpa_end_cmp_ext { #define BNXT_NUM_TESTS(bp) 0 -#define BNXT_DEFAULT_RX_RING_SIZE 1023 -#define BNXT_DEFAULT_TX_RING_SIZE 512 +#define BNXT_DEFAULT_RX_RING_SIZE 511 +#define BNXT_DEFAULT_TX_RING_SIZE 511 #define MAX_TPA 64 From d5c91fb72f1652ea3026925240a0998a42ddb16b Mon Sep 17 00:00:00 2001 From: Jon Paul Maloy Date: Wed, 10 Feb 2016 16:14:57 -0500 Subject: [PATCH 215/489] tipc: fix premature addition of node to lookup table In commit 5266698661401a ("tipc: let broadcast packet reception use new link receive function") we introduced a new per-node broadcast reception link instance. This link is created at the moment the node itself is created. Unfortunately, the allocation is done after the node instance has already been added to the node lookup hash table. This creates a potential race condition, where arriving broadcast packets are able to find and access the node before it has been fully initialized, and before the above mentioned link has been created. The result is occasional crashes in the function tipc_bcast_rcv(), which is trying to access the not-yet existing link. We fix this by deferring the addition of the node instance until after it has been fully initialized in the function tipc_node_create(). Acked-by: Ying Xue Signed-off-by: Jon Maloy Signed-off-by: David S. Miller --- net/tipc/node.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/net/tipc/node.c b/net/tipc/node.c index fa97d9649a28..9d7a16fc5ca4 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -346,12 +346,6 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) skb_queue_head_init(&n->bc_entry.inputq2); for (i = 0; i < MAX_BEARERS; i++) spin_lock_init(&n->links[i].lock); - hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); - list_for_each_entry_rcu(temp_node, &tn->node_list, list) { - if (n->addr < temp_node->addr) - break; - } - list_add_tail_rcu(&n->list, &temp_node->list); n->state = SELF_DOWN_PEER_LEAVING; n->signature = INVALID_NODE_SIG; n->active_links[0] = INVALID_BEARER_ID; @@ -372,6 +366,12 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u16 capabilities) tipc_node_get(n); setup_timer(&n->timer, tipc_node_timeout, (unsigned long)n); n->keepalive_intv = U32_MAX; + hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]); + list_for_each_entry_rcu(temp_node, &tn->node_list, list) { + if (n->addr < temp_node->addr) + break; + } + list_add_tail_rcu(&n->list, &temp_node->list); exit: spin_unlock_bh(&tn->node_list_lock); return n; From bd16a7248042dc62285fdc5598ec4888c0865819 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 11 Feb 2016 11:44:48 +0100 Subject: [PATCH 216/489] net: dsa: mv88e6xxx: Add support for Marvell 88E6240 The Marvell 88E6240 has been tested successfully without further changes. Add entry to the table of supported devices. Signed-off-by: Sascha Hauer Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6352.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/dsa/mv88e6352.c b/drivers/net/dsa/mv88e6352.c index cc6c54553418..a47f52f44b0d 100644 --- a/drivers/net/dsa/mv88e6352.c +++ b/drivers/net/dsa/mv88e6352.c @@ -25,6 +25,7 @@ static const struct mv88e6xxx_switch_id mv88e6352_table[] = { { PORT_SWITCH_ID_6172, "Marvell 88E6172" }, { PORT_SWITCH_ID_6176, "Marvell 88E6176" }, + { PORT_SWITCH_ID_6240, "Marvell 88E6240" }, { PORT_SWITCH_ID_6320, "Marvell 88E6320" }, { PORT_SWITCH_ID_6320_A1, "Marvell 88E6320 (A1)" }, { PORT_SWITCH_ID_6320_A2, "Marvell 88e6320 (A2)" }, From a407054f830ca9a28febdeeeaa34d2ed420b9ed3 Mon Sep 17 00:00:00 2001 From: Sascha Hauer Date: Thu, 11 Feb 2016 11:44:49 +0100 Subject: [PATCH 217/489] net: dsa: remove phy_disconnect from error path The phy has not been initialized, disconnecting it in the error path results in a NULL pointer exception. Drop the phy_disconnect from the error path. Signed-off-by: Sascha Hauer Reviewed-by: Andrew Lunn Acked-by: Neil Armstrong Signed-off-by: David S. Miller --- net/dsa/slave.c | 1 - 1 file changed, 1 deletion(-) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 40b9ca72aae3..91e3b2ff364a 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1194,7 +1194,6 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, if (ret) { netdev_err(master, "error %d registering interface %s\n", ret, slave_dev->name); - phy_disconnect(p->phy); ds->ports[port] = NULL; free_netdev(slave_dev); return ret; From 6c5d89a34a486ad782dfb5b6b3b8fb4976ae7619 Mon Sep 17 00:00:00 2001 From: Ken Kawasaki Date: Thu, 11 Feb 2016 20:27:04 +0900 Subject: [PATCH 218/489] pcnet_cs: add new id add new id (CONTEC C-NET(PC)C-100TX2) Signed-off-by: Ken Kawasaki Signed-off-by: David S. Miller --- drivers/net/ethernet/8390/pcnet_cs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/8390/pcnet_cs.c b/drivers/net/ethernet/8390/pcnet_cs.c index 2777289a26c0..2f79d29f17f2 100644 --- a/drivers/net/ethernet/8390/pcnet_cs.c +++ b/drivers/net/ethernet/8390/pcnet_cs.c @@ -1501,6 +1501,7 @@ static const struct pcmcia_device_id pcnet_ids[] = { PCMCIA_DEVICE_MANF_CARD(0x026f, 0x030a), PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1103), PCMCIA_DEVICE_MANF_CARD(0x0274, 0x1121), + PCMCIA_DEVICE_MANF_CARD(0xc001, 0x0009), PCMCIA_DEVICE_PROD_ID12("2408LAN", "Ethernet", 0x352fff7f, 0x00b2e941), PCMCIA_DEVICE_PROD_ID1234("Socket", "CF 10/100 Ethernet Card", "Revision B", "05/11/06", 0xb38bcc2e, 0x4de88352, 0xeaca6c8d, 0x7e57c22e), PCMCIA_DEVICE_PROD_ID123("Cardwell", "PCMCIA", "ETHERNET", 0x9533672e, 0x281f1c5d, 0x3ff7175b), From 372022830b06d9980c7e8b41fa0a4081cff883b0 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Feb 2016 08:58:18 -0800 Subject: [PATCH 219/489] tcp: do not set rtt_min to 1 There are some cases where rtt_us derives from deltas of jiffies, instead of using usec timestamps. Since we want to track minimal rtt, better to assume a delta of 0 jiffie might be in fact be very close to 1 jiffie. It is kind of sad jiffies_to_usecs(1) calls a function instead of simply using a constant. Fixes: f672258391b42 ("tcp: track min RTT using windowed min-filter") Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Cc: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 1c2a73406261..3b2c8e90a475 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2896,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) { const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; struct rtt_meas *m = tcp_sk(sk)->rtt_min; - struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now }; + struct rtt_meas rttm = { + .rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1), + .ts = now, + }; u32 elapsed; /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ From 3d65ae4634ed8350aee98a4e6f4e41fe40c7d282 Mon Sep 17 00:00:00 2001 From: Tahsin Erdogan Date: Tue, 16 Feb 2016 13:34:39 -0800 Subject: [PATCH 220/489] writeback: initialize inode members that track writeback history inode struct members that track cgroup writeback information should be reinitialized when inode gets allocated from kmem_cache. Otherwise, their values remain and get used by the new inode. Signed-off-by: Tahsin Erdogan Acked-by: Tejun Heo Fixes: d10c80955265 ("writeback: implement foreign cgroup inode bdi_writeback switching") Signed-off-by: Jens Axboe --- fs/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/fs/inode.c b/fs/inode.c index 9f62db3bcc3e..69b8b526c194 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -154,6 +154,12 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_rdev = 0; inode->dirtied_when = 0; +#ifdef CONFIG_CGROUP_WRITEBACK + inode->i_wb_frn_winner = 0; + inode->i_wb_frn_avg_time = 0; + inode->i_wb_frn_history = 0; +#endif + if (security_inode_alloc(inode)) goto out; spin_lock_init(&inode->i_lock); From 729235554d805c63e5e274fcc6a98e71015dd847 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Feb 2016 22:50:29 -0800 Subject: [PATCH 221/489] tcp: md5: release request socket instead of listener If tcp_v4_inbound_md5_hash() returns an error, we must release the refcount on the request socket, not on the listener. The bug was added for IPv4 only. Fixes: 079096f103fac ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7f6ff037adaf..c84477949d3a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1600,8 +1600,10 @@ process: struct sock *nsk = NULL; sk = req->rsk_listener; - if (tcp_v4_inbound_md5_hash(sk, skb)) - goto discard_and_relse; + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + reqsk_put(req); + goto discard_it; + } if (likely(sk->sk_state == TCP_LISTEN)) { nsk = tcp_check_req(sk, skb, req, false); } else { From aac8d3c282e024c344c5b86dc1eab7af88bb9716 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 12 Feb 2016 16:42:14 +0100 Subject: [PATCH 222/489] qmi_wwan: add "4G LTE usb-modem U901" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thomas reports: T: Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=05c6 ProdID=6001 Rev=00.00 S: Manufacturer=USB Modem S: Product=USB Modem S: SerialNumber=1234567890ABCDEF C: #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage Reported-by: Thomas Schäfer Signed-off-by: Bjørn Mork Signed-off-by: David S. Miller --- drivers/net/usb/qmi_wwan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 23e9880791fc..570deef53f74 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -637,6 +637,7 @@ static const struct usb_device_id products[] = { /* 3. Combined interface devices matching on interface number */ {QMI_FIXED_INTF(0x0408, 0xea42, 4)}, /* Yota / Megafon M100-1 */ + {QMI_FIXED_INTF(0x05c6, 0x6001, 3)}, /* 4G LTE usb-modem U901 */ {QMI_FIXED_INTF(0x05c6, 0x7000, 0)}, {QMI_FIXED_INTF(0x05c6, 0x7001, 1)}, {QMI_FIXED_INTF(0x05c6, 0x7002, 1)}, From 8ae22cb419ad0bae84d3ed9784c92922fa6343eb Mon Sep 17 00:00:00 2001 From: Dave Airlie Date: Wed, 17 Feb 2016 11:36:38 +1000 Subject: [PATCH 223/489] Revert "drm/dp/mst: change MST detection scheme" This reverts commit cfcfa086d43ced33e1099b9befb12f17fca102e1. This causes the tiling properties to break in some unexpected ways, Revert it for now. Cc: stable@vger.kernel.org Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_dp_mst_topology.c | 37 +++++++++++++-------------- 1 file changed, 18 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c index 8ae13de272c4..27fbd79d0daf 100644 --- a/drivers/gpu/drm/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/drm_dp_mst_topology.c @@ -1159,11 +1159,13 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb, drm_dp_put_port(port); goto out; } - - drm_mode_connector_set_tile_property(port->connector); - + if (port->port_num >= DP_MST_LOGICAL_PORT_0) { + port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc); + drm_mode_connector_set_tile_property(port->connector); + } (*mstb->mgr->cbs->register_connector)(port->connector); } + out: /* put reference to this port */ drm_dp_put_port(port); @@ -1188,8 +1190,8 @@ static void drm_dp_update_port(struct drm_dp_mst_branch *mstb, port->ddps = conn_stat->displayport_device_plug_status; if (old_ddps != port->ddps) { - dowork = true; if (port->ddps) { + dowork = true; } else { port->available_pbn = 0; } @@ -1294,13 +1296,8 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m if (port->input) continue; - if (!port->ddps) { - if (port->cached_edid) { - kfree(port->cached_edid); - port->cached_edid = NULL; - } + if (!port->ddps) continue; - } if (!port->available_pbn) drm_dp_send_enum_path_resources(mgr, mstb, port); @@ -1311,12 +1308,6 @@ static void drm_dp_check_and_send_link_address(struct drm_dp_mst_topology_mgr *m drm_dp_check_and_send_link_address(mgr, mstb_child); drm_dp_put_mst_branch_device(mstb_child); } - } else if (port->pdt == DP_PEER_DEVICE_SST_SINK || - port->pdt == DP_PEER_DEVICE_DP_LEGACY_CONV) { - if (!port->cached_edid) { - port->cached_edid = - drm_get_edid(port->connector, &port->aux.ddc); - } } } } @@ -1336,8 +1327,6 @@ static void drm_dp_mst_link_probe_work(struct work_struct *work) drm_dp_check_and_send_link_address(mgr, mstb); drm_dp_put_mst_branch_device(mstb); } - - (*mgr->cbs->hotplug)(mgr); } static bool drm_dp_validate_guid(struct drm_dp_mst_topology_mgr *mgr, @@ -1597,6 +1586,7 @@ static void drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, for (i = 0; i < txmsg->reply.u.link_addr.nports; i++) { drm_dp_add_port(mstb, mgr->dev, &txmsg->reply.u.link_addr.ports[i]); } + (*mgr->cbs->hotplug)(mgr); } } else { mstb->link_address_sent = false; @@ -2293,6 +2283,8 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) drm_dp_update_port(mstb, &msg.u.conn_stat); DRM_DEBUG_KMS("Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", msg.u.conn_stat.port_number, msg.u.conn_stat.legacy_device_plug_status, msg.u.conn_stat.displayport_device_plug_status, msg.u.conn_stat.message_capability_status, msg.u.conn_stat.input_port, msg.u.conn_stat.peer_device_type); + (*mgr->cbs->hotplug)(mgr); + } else if (msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { drm_dp_send_up_ack_reply(mgr, mgr->mst_primary, msg.req_type, seqno, false); if (!mstb) @@ -2379,6 +2371,10 @@ enum drm_connector_status drm_dp_mst_detect_port(struct drm_connector *connector case DP_PEER_DEVICE_SST_SINK: status = connector_status_connected; + /* for logical ports - cache the EDID */ + if (port->port_num >= 8 && !port->cached_edid) { + port->cached_edid = drm_get_edid(connector, &port->aux.ddc); + } break; case DP_PEER_DEVICE_DP_LEGACY_CONV: if (port->ldps) @@ -2433,7 +2429,10 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_ if (port->cached_edid) edid = drm_edid_duplicate(port->cached_edid); - + else { + edid = drm_get_edid(connector, &port->aux.ddc); + drm_mode_connector_set_tile_property(connector); + } port->has_audio = drm_detect_monitor_audio(edid); drm_dp_put_port(port); return edid; From 34855706c30d52b0a744da44348b5d1cc39fbe51 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 16 Feb 2016 14:25:00 +0100 Subject: [PATCH 224/489] drm/qxl: use kmalloc_array to alloc reloc_info in qxl_process_single_command This avoids integer overflows on 32bit machines when calculating reloc_info size, as reported by Alan Cox. Cc: stable@vger.kernel.org Cc: gnomes@lxorguk.ukuu.org.uk Signed-off-by: Gerd Hoffmann Reviewed-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/qxl/qxl_ioctl.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/qxl/qxl_ioctl.c b/drivers/gpu/drm/qxl/qxl_ioctl.c index 2ae8577497ca..7c2e78201ead 100644 --- a/drivers/gpu/drm/qxl/qxl_ioctl.c +++ b/drivers/gpu/drm/qxl/qxl_ioctl.c @@ -168,7 +168,8 @@ static int qxl_process_single_command(struct qxl_device *qdev, cmd->command_size)) return -EFAULT; - reloc_info = kmalloc(sizeof(struct qxl_reloc_info) * cmd->relocs_num, GFP_KERNEL); + reloc_info = kmalloc_array(cmd->relocs_num, + sizeof(struct qxl_reloc_info), GFP_KERNEL); if (!reloc_info) return -ENOMEM; From e8235891b33799d597ff4ab5e45afe173a65da30 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 12 Feb 2016 20:30:27 +0100 Subject: [PATCH 225/489] drm: No-Op redundant calls to drm_vblank_off() (v2) Otherwise if a kms driver calls into drm_vblank_off() more than once before calling drm_vblank_on() again, the redundant calls to vblank_disable_and_save() will call drm_update_vblank_count() while hw vblank counters and vblank timestamping are in a undefined state during modesets, dpms off etc. At least with the legacy drm helpers it is not unusual to get multiple calls to drm_vblank_off and drm_vblank_on, e.g., half a dozen calls to drm_vblank_off and two calls to drm_vblank_on were observed on radeon-kms during dpms-off -> dpms-on transition. We don't no-op calls from atomic modesetting drivers, as they should do a proper job of tracking hw state. Fixes large jumps of the software maintained vblank counter due to the hardware vblank counter resetting to zero during dpms off or modeset, e.g., if radeon-kms is modified to use drm_vblank_off/on instead of drm_vblank_pre/post_modeset(). This fixes a regression caused by the changes made to drm_update_vblank_count() in Linux 4.4. v2: Don't no-op on atomic modesetting drivers, per suggestion of Daniel Vetter. Signed-off-by: Mario Kleiner Reviewed-by: Daniel Vetter Cc: # 4.4+ Cc: michel@daenzer.net Cc: vbabka@suse.cz Cc: ville.syrjala@linux.intel.com Cc: alexander.deucher@amd.com Cc: christian.koenig@amd.com Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_irq.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index d12a4efa651b..685b0ebe5fb2 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -1316,7 +1316,13 @@ void drm_vblank_off(struct drm_device *dev, unsigned int pipe) spin_lock_irqsave(&dev->event_lock, irqflags); spin_lock(&dev->vbl_lock); - vblank_disable_and_save(dev, pipe); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + + /* Avoid redundant vblank disables without previous drm_vblank_on(). */ + if (drm_core_check_feature(dev, DRIVER_ATOMIC) || !vblank->inmodeset) + vblank_disable_and_save(dev, pipe); + wake_up(&vblank->queue); /* @@ -1418,6 +1424,9 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) return; spin_lock_irqsave(&dev->vbl_lock, irqflags); + DRM_DEBUG_VBL("crtc %d, vblank enabled %d, inmodeset %d\n", + pipe, vblank->enabled, vblank->inmodeset); + /* Drop our private "prevent drm_vblank_get" refcount */ if (vblank->inmodeset) { atomic_dec(&vblank->refcount); From 99b8e71597fadd6b2ac85e6e10f221f79dd9c1c1 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 12 Feb 2016 20:30:28 +0100 Subject: [PATCH 226/489] drm: Prevent vblank counter bumps > 1 with active vblank clients. (v2) This fixes a regression introduced by the new drm_update_vblank_count() implementation in Linux 4.4: Restrict the bump of the software vblank counter in drm_update_vblank_count() to a safe maximum value of +1 whenever there is the possibility that concurrent readers of vblank timestamps could be active at the moment, as the current implementation of the timestamp caching and updating is not safe against concurrent readers for calls to store_vblank() with a bump of anything but +1. A bump != 1 would very likely return corrupted timestamps to userspace, because the same slot in the cache could be concurrently written by store_vblank() and read by one of those readers in a non-atomic fashion and without the read-retry logic detecting this collision. Concurrent readers can exist while drm_update_vblank_count() is called from the drm_vblank_off() or drm_vblank_on() functions or other non-vblank- irq callers. However, all those calls are happening with the vbl_lock locked thereby preventing a drm_vblank_get(), so the vblank refcount can't increase while drm_update_vblank_count() is executing. Therefore a zero vblank refcount during execution of that function signals that is safe for arbitrary counter bumps if called from outside vblank irq, whereas a non-zero count is not safe. Whenever the function is called from vblank irq, we have to assume concurrent readers could show up any time during its execution, even if the refcount is currently zero, as vblank irqs are usually only enabled due to the presence of readers, and because when it is called from vblank irq it can't hold the vbl_lock to protect it from sudden bumps in vblank refcount. Therefore also restrict bumps to +1 when the function is called from vblank irq. Such bumps of more than +1 can happen at other times than reenabling vblank irqs, e.g., when regular vblank interrupts get delayed by more than 1 frame due to long held locks, long irq off periods, realtime preemption on RT kernels, or system management interrupts. A better solution would be to rewrite the timestamp caching to use full seqlocks to allow concurrent writes and reads for arbitrary vblank counter increments. v2: Add code comment that this is essentially a hack and should be replaced by a full seqlock implementation for caching of timestamps. Signed-off-by: Mario Kleiner Reviewed-by: Daniel Vetter Cc: # 4.4+ Cc: michel@daenzer.net Cc: vbabka@suse.cz Cc: ville.syrjala@linux.intel.com Cc: daniel.vetter@ffwll.ch Cc: dri-devel@lists.freedesktop.org Cc: alexander.deucher@amd.com Cc: christian.koenig@amd.com Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_irq.c | 43 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 685b0ebe5fb2..0ac2608ba150 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -224,6 +224,49 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; } + /* + * FIMXE: Need to replace this hack with proper seqlocks. + * + * Restrict the bump of the software vblank counter to a safe maximum + * value of +1 whenever there is the possibility that concurrent readers + * of vblank timestamps could be active at the moment, as the current + * implementation of the timestamp caching and updating is not safe + * against concurrent readers for calls to store_vblank() with a bump + * of anything but +1. A bump != 1 would very likely return corrupted + * timestamps to userspace, because the same slot in the cache could + * be concurrently written by store_vblank() and read by one of those + * readers without the read-retry logic detecting the collision. + * + * Concurrent readers can exist when we are called from the + * drm_vblank_off() or drm_vblank_on() functions and other non-vblank- + * irq callers. However, all those calls to us are happening with the + * vbl_lock locked to prevent drm_vblank_get(), so the vblank refcount + * can't increase while we are executing. Therefore a zero refcount at + * this point is safe for arbitrary counter bumps if we are called + * outside vblank irq, a non-zero count is not 100% safe. Unfortunately + * we must also accept a refcount of 1, as whenever we are called from + * drm_vblank_get() -> drm_vblank_enable() the refcount will be 1 and + * we must let that one pass through in order to not lose vblank counts + * during vblank irq off - which would completely defeat the whole + * point of this routine. + * + * Whenever we are called from vblank irq, we have to assume concurrent + * readers exist or can show up any time during our execution, even if + * the refcount is currently zero, as vblank irqs are usually only + * enabled due to the presence of readers, and because when we are called + * from vblank irq we can't hold the vbl_lock to protect us from sudden + * bumps in vblank refcount. Therefore also restrict bumps to +1 when + * called from vblank irq. + */ + if ((diff > 1) && (atomic_read(&vblank->refcount) > 1 || + (flags & DRM_CALLED_FROM_VBLIRQ))) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u " + "refcount %u, vblirq %u\n", pipe, diff, + atomic_read(&vblank->refcount), + (flags & DRM_CALLED_FROM_VBLIRQ) != 0); + diff = 1; + } + DRM_DEBUG_VBL("updating vblank count on crtc %u:" " current=%u, diff=%u, hw=%u hw_last=%u\n", pipe, vblank->count, diff, cur_vblank, vblank->last); From c61934ed9a0e3911a9935df26858726a7ec35ec0 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 12 Feb 2016 20:30:29 +0100 Subject: [PATCH 227/489] drm: Fix drm_vblank_pre/post_modeset regression from Linux 4.4 Changes to drm_update_vblank_count() in Linux 4.4 broke the behaviour of the pre/post modeset functions as the new update code doesn't deal with hw vblank counter resets inbetween calls to drm_vblank_pre_modeset an drm_vblank_post_modeset, as it should. This causes mistreatment of such hw counter resets as counter wraparound, and thereby large forward jumps of the software vblank counter which in turn cause vblank event dispatching and vblank waits to fail/hang --> userspace clients hang. This symptom was reported on radeon-kms to cause a infinite hang of KDE Plasma 5 shell's login procedure, preventing users from logging in. Fix this by detecting when drm_update_vblank_count() is called inside a pre->post modeset interval. If so, clamp valid vblank increments to the safe values 0 and 1, pretty much restoring the update behavior of the old update code of Linux 4.3 and earlier. Also reset the last recorded hw vblank count at call to drm_vblank_post_modeset() to be safe against hw that after modesetting, dpms on etc. only fires its first vblank irq after drm_vblank_post_modeset() was already called. Reported-by: Vlastimil Babka Signed-off-by: Mario Kleiner Reviewed-by: Daniel Vetter Tested-by: Vlastimil Babka Cc: # 4.4+ Cc: michel@daenzer.net Cc: vbabka@suse.cz Cc: ville.syrjala@linux.intel.com Cc: daniel.vetter@ffwll.ch Cc: dri-devel@lists.freedesktop.org Cc: alexander.deucher@amd.com Cc: christian.koenig@amd.com Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_irq.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 0ac2608ba150..5510899eee1d 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -224,6 +224,21 @@ static void drm_update_vblank_count(struct drm_device *dev, unsigned int pipe, diff = (flags & DRM_CALLED_FROM_VBLIRQ) != 0; } + /* + * Within a drm_vblank_pre_modeset - drm_vblank_post_modeset + * interval? If so then vblank irqs keep running and it will likely + * happen that the hardware vblank counter is not trustworthy as it + * might reset at some point in that interval and vblank timestamps + * are not trustworthy either in that interval. Iow. this can result + * in a bogus diff >> 1 which must be avoided as it would cause + * random large forward jumps of the software vblank counter. + */ + if (diff > 1 && (vblank->inmodeset & 0x2)) { + DRM_DEBUG_VBL("clamping vblank bump to 1 on crtc %u: diffr=%u" + " due to pre-modeset.\n", pipe, diff); + diff = 1; + } + /* * FIMXE: Need to replace this hack with proper seqlocks. * @@ -1578,6 +1593,7 @@ void drm_vblank_post_modeset(struct drm_device *dev, unsigned int pipe) if (vblank->inmodeset) { spin_lock_irqsave(&dev->vbl_lock, irqflags); dev->vblank_disable_allowed = true; + drm_reset_vblank_timestamp(dev, pipe); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); if (vblank->inmodeset & 0x2) From bb74fc1bf3072bd3ab4ed5f43afd287a63baf2d7 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 12 Feb 2016 20:30:30 +0100 Subject: [PATCH 228/489] drm: Fix treatment of drm_vblank_offdelay in drm_vblank_on() (v2) drm_vblank_offdelay can have three different types of values: < 0 is to be always treated the same as dev->vblank_disable_immediate = 0 is to be treated as "never disable vblanks" > 0 is to be treated as disable immediate if kms driver wants it that way via dev->vblank_disable_immediate. Otherwise it is a disable timeout in msecs. This got broken in Linux 3.18+ for the implementation of drm_vblank_on. If the user specified a value of zero which should always reenable vblank irqs in this function, a kms driver could override the users choice by setting vblank_disable_immediate to true. This patch fixes the regression and keeps the user in control. v2: Only reenable vblank if there are clients left or the user requested to "never disable vblanks" via offdelay 0. Enabling vblanks even in the "delayed disable" case (offdelay > 0) was specifically added by Ville in commit cd19e52aee922 ("drm: Kick start vblank interrupts at drm_vblank_on()"), but after discussion it turns out that this was done by accident. Citing Ville: "I think it just ended up as a mess due to changing some of the semantics of offdelay<0 vs. offdelay==0 vs. disable_immediate during the review of the series. So yeah, given how drm_vblank_put() works now, I'd just make this check for offdelay==0." Signed-off-by: Mario Kleiner Reviewed-by: Daniel Vetter Cc: # 3.18+ Cc: michel@daenzer.net Cc: vbabka@suse.cz Cc: ville.syrjala@linux.intel.com Cc: daniel.vetter@ffwll.ch Cc: dri-devel@lists.freedesktop.org Cc: alexander.deucher@amd.com Cc: christian.koenig@amd.com Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_irq.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c index 5510899eee1d..1fe14579e8c9 100644 --- a/drivers/gpu/drm/drm_irq.c +++ b/drivers/gpu/drm/drm_irq.c @@ -1497,8 +1497,7 @@ void drm_vblank_on(struct drm_device *dev, unsigned int pipe) * re-enable interrupts if there are users left, or the * user wishes vblank interrupts to be enabled all the time. */ - if (atomic_read(&vblank->refcount) != 0 || - (!dev->vblank_disable_immediate && drm_vblank_offdelay == 0)) + if (atomic_read(&vblank->refcount) != 0 || drm_vblank_offdelay == 0) WARN_ON(drm_vblank_enable(dev, pipe)); spin_unlock_irqrestore(&dev->vbl_lock, irqflags); } From e0b34e3857004ac2257458d6354c31349f51e207 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 12 Feb 2016 20:30:31 +0100 Subject: [PATCH 229/489] drm/radeon/pm: Handle failure of drm_vblank_get. Make sure that drm_vblank_get/put() stay balanced in case drm_vblank_get fails, by skipping the corresponding put. Signed-off-by: Mario Kleiner Reviewed-by: Daniel Vetter Cc: michel@daenzer.net Cc: dri-devel@lists.freedesktop.org Cc: alexander.deucher@amd.com Cc: christian.koenig@amd.com Signed-off-by: Dave Airlie --- drivers/gpu/drm/radeon/radeon_pm.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 460c8f2989da..248c5a9fb0b6 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -276,8 +276,12 @@ static void radeon_pm_set_clocks(struct radeon_device *rdev) if (rdev->irq.installed) { for (i = 0; i < rdev->num_crtc; i++) { if (rdev->pm.active_crtcs & (1 << i)) { - rdev->pm.req_vblank |= (1 << i); - drm_vblank_get(rdev->ddev, i); + /* This can fail if a modeset is in progress */ + if (drm_vblank_get(rdev->ddev, i) == 0) + rdev->pm.req_vblank |= (1 << i); + else + DRM_DEBUG_DRIVER("crtc %d no vblank, can glitch\n", + i); } } } From ff683df7bf34f90766a50c7e7454e219aef2710e Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 12 Feb 2016 20:30:32 +0100 Subject: [PATCH 230/489] drm/nouveau/display: Enable vblank irqs after display engine is on again. In the display resume path, move the calls to drm_vblank_on() after the point when the display engine is running again. Since changes were made to drm_update_vblank_count() in Linux 4.4+ to emulate hw vblank counters via vblank timestamping, the function drm_vblank_on() now needs working high precision vblank timestamping and therefore working scanout position queries at time of call. These don't work before the display engine gets restarted, causing miscalculation of vblank counter increments and thereby large forward jumps in vblank count at display resume. These jumps can cause client hangs on resume, or desktop hangs in the case of composited desktops. Fix this Linux 4.4 regression by reordering calls accordingly. Signed-off-by: Mario Kleiner Cc: # 4.4+ Cc: Ben Skeggs Cc: ville.syrjala@linux.intel.com Cc: daniel.vetter@ffwll.ch Cc: dri-devel@lists.freedesktop.org Reviewed-by: Daniel Vetter Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_display.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 24be27d3cd18..20935eb2a09e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -635,10 +635,6 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) nv_crtc->lut.depth = 0; } - /* Make sure that drm and hw vblank irqs get resumed if needed. */ - for (head = 0; head < dev->mode_config.num_crtc; head++) - drm_vblank_on(dev, head); - /* This should ensure we don't hit a locking problem when someone * wakes us up via a connector. We should never go into suspend * while the display is on anyways. @@ -648,6 +644,10 @@ nouveau_display_resume(struct drm_device *dev, bool runtime) drm_helper_resume_force_mode(dev); + /* Make sure that drm and hw vblank irqs get resumed if needed. */ + for (head = 0; head < dev->mode_config.num_crtc; head++) + drm_vblank_on(dev, head); + list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) { struct nouveau_crtc *nv_crtc = nouveau_crtc(crtc); From dada168b3b76439d83aff34f8fbd9c512c2d136a Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Sat, 6 Feb 2016 23:25:28 -0500 Subject: [PATCH 231/489] drm/qxl: fix erroneous return value The qxl_gem_prime_mmap() function returns ENOSYS instead of -ENOSYS Signed-off-by: Anton Protopopov Signed-off-by: Dave Airlie --- drivers/gpu/drm/qxl/qxl_prime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/qxl/qxl_prime.c b/drivers/gpu/drm/qxl/qxl_prime.c index 3d031b50a8fd..9f029dda1f07 100644 --- a/drivers/gpu/drm/qxl/qxl_prime.c +++ b/drivers/gpu/drm/qxl/qxl_prime.c @@ -68,5 +68,5 @@ int qxl_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *area) { WARN_ONCE(1, "not implemented"); - return ENOSYS; + return -ENOSYS; } From 52499d93d6dec3872de3b982219af6d4c182a452 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Fri, 12 Feb 2016 12:40:31 +0100 Subject: [PATCH 232/489] s390/maccess: reduce stnsm instructions When fixing the DAT off bug ("s390: fix DAT off memory access, e.g. on kdump") both Christian and I missed that we can save an additional stnsm instruction. This saves us a couple of cycles which could improve the speed of memcpy_real. Signed-off-by: Heiko Carstens Signed-off-by: Martin Schwidefsky --- arch/s390/mm/maccess.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c index 350b0acd7f52..792f9c63fbca 100644 --- a/arch/s390/mm/maccess.c +++ b/arch/s390/mm/maccess.c @@ -93,15 +93,17 @@ static int __memcpy_real(void *dest, void *src, size_t count) */ int memcpy_real(void *dest, void *src, size_t count) { + int irqs_disabled, rc; unsigned long flags; - int rc; if (!count) return 0; - local_irq_save(flags); - __arch_local_irq_stnsm(0xfbUL); + flags = __arch_local_irq_stnsm(0xf8UL); + irqs_disabled = arch_irqs_disabled_flags(flags); + if (!irqs_disabled) + trace_hardirqs_off(); rc = __memcpy_real(dest, src, count); - if (!arch_irqs_disabled_flags(flags)) + if (!irqs_disabled) trace_hardirqs_on(); __arch_local_irq_ssm(flags); return rc; From ee9737c924706aaa72c2ead93e3ad5644681dc1c Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Thu, 11 Feb 2016 14:24:16 -0700 Subject: [PATCH 233/489] x86/uaccess/64: Make the __copy_user_nocache() assembly code more readable Add comments to __copy_user_nocache() to clarify its procedures and alignment requirements. Also change numeric branch target labels to named local labels. No code changed: arch/x86/lib/copy_user_64.o: text data bss dec hex filename 1239 0 0 1239 4d7 copy_user_64.o.before 1239 0 0 1239 4d7 copy_user_64.o.after md5: 58bed94c2db98c1ca9a2d46d0680aaae copy_user_64.o.before.asm 58bed94c2db98c1ca9a2d46d0680aaae copy_user_64.o.after.asm Signed-off-by: Toshi Kani Cc: Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Toshi Kani Cc: brian.boylston@hpe.com Cc: dan.j.williams@intel.com Cc: linux-nvdimm@lists.01.org Cc: micah.parrish@hpe.com Cc: ross.zwisler@linux.intel.com Cc: vishal.l.verma@intel.com Link: http://lkml.kernel.org/r/1455225857-12039-2-git-send-email-toshi.kani@hpe.com [ Small readability edits and added object file comparison. ] Signed-off-by: Ingo Molnar --- arch/x86/lib/copy_user_64.S | 114 +++++++++++++++++++++++------------- 1 file changed, 73 insertions(+), 41 deletions(-) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 982ce34f4a9b..a644aad1f112 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -232,17 +232,30 @@ ENDPROC(copy_user_enhanced_fast_string) /* * copy_user_nocache - Uncached memory copy with exception handling - * This will force destination/source out of cache for more performance. + * This will force destination out of cache for more performance. + * + * Note: Cached memory copy is used when destination or size is not + * naturally aligned. That is: + * - Require 8-byte alignment when size is 8 bytes or larger. */ ENTRY(__copy_user_nocache) ASM_STAC + + /* If size is less than 8 bytes, go to byte copy */ cmpl $8,%edx - jb 20f /* less then 8 bytes, go to byte copy loop */ + jb .L_1b_cache_copy_entry + + /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION + + /* Set 4x8-byte copy count and remainder */ movl %edx,%ecx andl $63,%edx shrl $6,%ecx - jz 17f + jz .L_8b_nocache_copy_entry /* jump if count is 0 */ + + /* Perform 4x8-byte nocache loop-copy */ +.L_4x8b_nocache_copy_loop: 1: movq (%rsi),%r8 2: movq 1*8(%rsi),%r9 3: movq 2*8(%rsi),%r10 @@ -262,60 +275,79 @@ ENTRY(__copy_user_nocache) leaq 64(%rsi),%rsi leaq 64(%rdi),%rdi decl %ecx - jnz 1b -17: movl %edx,%ecx + jnz .L_4x8b_nocache_copy_loop + + /* Set 8-byte copy count and remainder */ +.L_8b_nocache_copy_entry: + movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz 20f -18: movq (%rsi),%r8 -19: movnti %r8,(%rdi) + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 8-byte nocache loop-copy */ +.L_8b_nocache_copy_loop: +20: movq (%rsi),%r8 +21: movnti %r8,(%rdi) leaq 8(%rsi),%rsi leaq 8(%rdi),%rdi decl %ecx - jnz 18b -20: andl %edx,%edx - jz 23f + jnz .L_8b_nocache_copy_loop + + /* If no byte left, we're done */ +.L_1b_cache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* Perform byte "cache" loop-copy for the remainder */ movl %edx,%ecx -21: movb (%rsi),%al -22: movb %al,(%rdi) +.L_1b_cache_copy_loop: +40: movb (%rsi),%al +41: movb %al,(%rdi) incq %rsi incq %rdi decl %ecx - jnz 21b -23: xorl %eax,%eax + jnz .L_1b_cache_copy_loop + + /* Finished copying; fence the prior stores */ +.L_finish_copy: + xorl %eax,%eax ASM_CLAC sfence ret .section .fixup,"ax" -30: shll $6,%ecx +.L_fixup_4x8b_copy: + shll $6,%ecx addl %ecx,%edx - jmp 60f -40: lea (%rdx,%rcx,8),%rdx - jmp 60f -50: movl %ecx,%edx -60: sfence + jmp .L_fixup_handle_tail +.L_fixup_8b_copy: + lea (%rdx,%rcx,8),%rdx + jmp .L_fixup_handle_tail +.L_fixup_1b_copy: + movl %ecx,%edx +.L_fixup_handle_tail: + sfence jmp copy_user_handle_tail .previous - _ASM_EXTABLE(1b,30b) - _ASM_EXTABLE(2b,30b) - _ASM_EXTABLE(3b,30b) - _ASM_EXTABLE(4b,30b) - _ASM_EXTABLE(5b,30b) - _ASM_EXTABLE(6b,30b) - _ASM_EXTABLE(7b,30b) - _ASM_EXTABLE(8b,30b) - _ASM_EXTABLE(9b,30b) - _ASM_EXTABLE(10b,30b) - _ASM_EXTABLE(11b,30b) - _ASM_EXTABLE(12b,30b) - _ASM_EXTABLE(13b,30b) - _ASM_EXTABLE(14b,30b) - _ASM_EXTABLE(15b,30b) - _ASM_EXTABLE(16b,30b) - _ASM_EXTABLE(18b,40b) - _ASM_EXTABLE(19b,40b) - _ASM_EXTABLE(21b,50b) - _ASM_EXTABLE(22b,50b) + _ASM_EXTABLE(1b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(2b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(3b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(4b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(5b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(6b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(7b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(8b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(9b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(10b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(11b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(12b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(13b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(14b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(15b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) + _ASM_EXTABLE(20b,.L_fixup_8b_copy) + _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(40b,.L_fixup_1b_copy) + _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) From a82eee7424525e34e98d821dd059ce14560a1e35 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Thu, 11 Feb 2016 14:24:17 -0700 Subject: [PATCH 234/489] x86/uaccess/64: Handle the caching of 4-byte nocache copies properly in __copy_user_nocache() Data corruption issues were observed in tests which initiated a system crash/reset while accessing BTT devices. This problem is reproducible. The BTT driver calls pmem_rw_bytes() to update data in pmem devices. This interface calls __copy_user_nocache(), which uses non-temporal stores so that the stores to pmem are persistent. __copy_user_nocache() uses non-temporal stores when a request size is 8 bytes or larger (and is aligned by 8 bytes). The BTT driver updates the BTT map table, which entry size is 4 bytes. Therefore, updates to the map table entries remain cached, and are not written to pmem after a crash. Change __copy_user_nocache() to use non-temporal store when a request size is 4 bytes. The change extends the current byte-copy path for a less-than-8-bytes request, and does not add any overhead to the regular path. Reported-and-tested-by: Micah Parrish Reported-and-tested-by: Brian Boylston Signed-off-by: Toshi Kani Cc: Cc: Andrew Morton Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Borislav Petkov Cc: Brian Gerst Cc: Dan Williams Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Ross Zwisler Cc: Thomas Gleixner Cc: Toshi Kani Cc: Vishal Verma Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455225857-12039-3-git-send-email-toshi.kani@hpe.com [ Small readability edits. ] Signed-off-by: Ingo Molnar --- arch/x86/lib/copy_user_64.S | 36 ++++++++++++++++++++++++++++++++---- 1 file changed, 32 insertions(+), 4 deletions(-) diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index a644aad1f112..27f89c79a44b 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -237,13 +237,14 @@ ENDPROC(copy_user_enhanced_fast_string) * Note: Cached memory copy is used when destination or size is not * naturally aligned. That is: * - Require 8-byte alignment when size is 8 bytes or larger. + * - Require 4-byte alignment when size is 4 bytes. */ ENTRY(__copy_user_nocache) ASM_STAC - /* If size is less than 8 bytes, go to byte copy */ + /* If size is less than 8 bytes, go to 4-byte copy */ cmpl $8,%edx - jb .L_1b_cache_copy_entry + jb .L_4b_nocache_copy_entry /* If destination is not 8-byte aligned, "cache" copy to align it */ ALIGN_DESTINATION @@ -282,7 +283,7 @@ ENTRY(__copy_user_nocache) movl %edx,%ecx andl $7,%edx shrl $3,%ecx - jz .L_1b_cache_copy_entry /* jump if count is 0 */ + jz .L_4b_nocache_copy_entry /* jump if count is 0 */ /* Perform 8-byte nocache loop-copy */ .L_8b_nocache_copy_loop: @@ -294,11 +295,33 @@ ENTRY(__copy_user_nocache) jnz .L_8b_nocache_copy_loop /* If no byte left, we're done */ -.L_1b_cache_copy_entry: +.L_4b_nocache_copy_entry: + andl %edx,%edx + jz .L_finish_copy + + /* If destination is not 4-byte aligned, go to byte copy: */ + movl %edi,%ecx + andl $3,%ecx + jnz .L_1b_cache_copy_entry + + /* Set 4-byte copy count (1 or 0) and remainder */ + movl %edx,%ecx + andl $3,%edx + shrl $2,%ecx + jz .L_1b_cache_copy_entry /* jump if count is 0 */ + + /* Perform 4-byte nocache copy: */ +30: movl (%rsi),%r8d +31: movnti %r8d,(%rdi) + leaq 4(%rsi),%rsi + leaq 4(%rdi),%rdi + + /* If no bytes left, we're done: */ andl %edx,%edx jz .L_finish_copy /* Perform byte "cache" loop-copy for the remainder */ +.L_1b_cache_copy_entry: movl %edx,%ecx .L_1b_cache_copy_loop: 40: movb (%rsi),%al @@ -323,6 +346,9 @@ ENTRY(__copy_user_nocache) .L_fixup_8b_copy: lea (%rdx,%rcx,8),%rdx jmp .L_fixup_handle_tail +.L_fixup_4b_copy: + lea (%rdx,%rcx,4),%rdx + jmp .L_fixup_handle_tail .L_fixup_1b_copy: movl %ecx,%edx .L_fixup_handle_tail: @@ -348,6 +374,8 @@ ENTRY(__copy_user_nocache) _ASM_EXTABLE(16b,.L_fixup_4x8b_copy) _ASM_EXTABLE(20b,.L_fixup_8b_copy) _ASM_EXTABLE(21b,.L_fixup_8b_copy) + _ASM_EXTABLE(30b,.L_fixup_4b_copy) + _ASM_EXTABLE(31b,.L_fixup_4b_copy) _ASM_EXTABLE(40b,.L_fixup_1b_copy) _ASM_EXTABLE(41b,.L_fixup_1b_copy) ENDPROC(__copy_user_nocache) From 12d319b920fa673a4d5e7c1785c5dc82dcd15257 Mon Sep 17 00:00:00 2001 From: Stefan Haberland Date: Fri, 12 Feb 2016 14:50:52 +0100 Subject: [PATCH 235/489] s390/dasd: fix performance drop Commit ca369d51b ("sd: Fix device-imposed transfer length limits") introduced a new queue limit max_dev_sectors which limits the maximum sectors for requests. The default value leads to small dasd requests and therefor to a performance drop. Set the max_dev_sectors value to the same value as the max_hw_sectors to use the maximum available request size for DASD devices. Signed-off-by: Stefan Haberland Cc: stable@vger.kernel.org # 4.4+ Signed-off-by: Martin Schwidefsky --- drivers/s390/block/dasd.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index 41605dac8309..c78db05e75b1 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -3035,6 +3035,7 @@ static void dasd_setup_queue(struct dasd_block *block) max = block->base->discipline->max_blocks << block->s2b_shift; } queue_flag_set_unlocked(QUEUE_FLAG_NONROT, block->request_queue); + block->request_queue->limits.max_dev_sectors = max; blk_queue_logical_block_size(block->request_queue, block->bp_block); blk_queue_max_hw_sectors(block->request_queue, max); From bd84f4ae9986ac9acd278566ccb39c60bc961abb Mon Sep 17 00:00:00 2001 From: John Youn Date: Mon, 15 Feb 2016 15:30:20 -0800 Subject: [PATCH 236/489] usb: dwc2: Add extra delay when forcing dr_mode Fixes an issue found on rockchip rk3036 and rk3188 SOC platforms. For some reason, the existing msleep(25) is not enough after the force mode. The following patch was reported to fix the issue. This does increase the probe delay again slightly, but not up to the level it was before the original series of patches that this fixes. It does not cause any other issues when tested on Synopsys HAPS and Altera socfpga platforms. Need to revisit this series next release to see if we can address these issues without having an unconditional delay. Fixes: 09c96980dc72 ("usb: dwc2: Add functions to set and clear force mode") Reported-by: Caesar Wang Reported-by: Michael Niewoehner Tested-by: Heiko Stuebner Tested-by: Caesar Wang Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c index e991d55914db..46c4ba75dc2a 100644 --- a/drivers/usb/dwc2/core.c +++ b/drivers/usb/dwc2/core.c @@ -619,6 +619,12 @@ void dwc2_force_dr_mode(struct dwc2_hsotg *hsotg) __func__, hsotg->dr_mode); break; } + + /* + * NOTE: This is required for some rockchip soc based + * platforms. + */ + msleep(50); } /* From c450960187f45d4260db87c7dd4fc0bceb5565d8 Mon Sep 17 00:00:00 2001 From: John Youn Date: Tue, 16 Feb 2016 20:10:53 -0800 Subject: [PATCH 237/489] usb: dwc3: Fix assignment of EP transfer resources The assignement of EP transfer resources was not handled properly in the dwc3 driver. Commit aebda6187181 ("usb: dwc3: Reset the transfer resource index on SET_INTERFACE") previously fixed one aspect of this where resources may be exhausted with multiple calls to SET_INTERFACE. However, it introduced an issue where composite devices with multiple interfaces can be assigned the same transfer resources for different endpoints. This patch solves both issues. The assignment of transfer resources cannot perfectly follow the data book due to the fact that the controller driver does not have all knowledge of the configuration in advance. It is given this information piecemeal by the composite gadget framework after every SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook programming model in this scenario can cause errors. For two reasons: 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION and SET_INTERFACE (8.1.5). This is incorrect in the scenario of multiple interfaces. 2) The databook does not mention doing more DEPXFERCFG for new endpoint on alt setting (8.1.6). The following simplified method is used instead: All hardware endpoints can be assigned a transfer resource and this setting will stay persistent until either a core reset or hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and do DEPXFERCFG for every hardware endpoint as well. We are guaranteed that there are as many transfer resources as endpoints. This patch triggers off of the calling dwc3_gadget_start_config() for EP0-out, which always happens first, and which should only happen in one of the above conditions. Fixes: aebda6187181 ("usb: dwc3: Reset the transfer resource index on SET_INTERFACE") Cc: # v3.2+ Reported-by: Ravi Babu Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc3/core.h | 1 - drivers/usb/dwc3/ep0.c | 5 --- drivers/usb/dwc3/gadget.c | 70 +++++++++++++++++++++++++++++---------- 3 files changed, 52 insertions(+), 24 deletions(-) diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index 29130682e547..e4f8b90d9627 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -856,7 +856,6 @@ struct dwc3 { unsigned pullups_connected:1; unsigned resize_fifos:1; unsigned setup_packet_pending:1; - unsigned start_config_issued:1; unsigned three_stage_setup:1; unsigned usb3_lpm_capable:1; diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c index 3a9354abcb68..8d6b75c2f53b 100644 --- a/drivers/usb/dwc3/ep0.c +++ b/drivers/usb/dwc3/ep0.c @@ -555,7 +555,6 @@ static int dwc3_ep0_set_config(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) int ret; u32 reg; - dwc->start_config_issued = false; cfg = le16_to_cpu(ctrl->wValue); switch (state) { @@ -737,10 +736,6 @@ static int dwc3_ep0_std_request(struct dwc3 *dwc, struct usb_ctrlrequest *ctrl) dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY"); ret = dwc3_ep0_set_isoch_delay(dwc, ctrl); break; - case USB_REQ_SET_INTERFACE: - dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE"); - dwc->start_config_issued = false; - /* Fall through */ default: dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver"); ret = dwc3_ep0_delegate_req(dwc, ctrl); diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 7d1dd82a95ac..2363bad45af8 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -385,24 +385,66 @@ static void dwc3_free_trb_pool(struct dwc3_ep *dep) dep->trb_pool_dma = 0; } +static int dwc3_gadget_set_xfer_resource(struct dwc3 *dwc, struct dwc3_ep *dep); + +/** + * dwc3_gadget_start_config - Configure EP resources + * @dwc: pointer to our controller context structure + * @dep: endpoint that is being enabled + * + * The assignment of transfer resources cannot perfectly follow the + * data book due to the fact that the controller driver does not have + * all knowledge of the configuration in advance. It is given this + * information piecemeal by the composite gadget framework after every + * SET_CONFIGURATION and SET_INTERFACE. Trying to follow the databook + * programming model in this scenario can cause errors. For two + * reasons: + * + * 1) The databook says to do DEPSTARTCFG for every SET_CONFIGURATION + * and SET_INTERFACE (8.1.5). This is incorrect in the scenario of + * multiple interfaces. + * + * 2) The databook does not mention doing more DEPXFERCFG for new + * endpoint on alt setting (8.1.6). + * + * The following simplified method is used instead: + * + * All hardware endpoints can be assigned a transfer resource and this + * setting will stay persistent until either a core reset or + * hibernation. So whenever we do a DEPSTARTCFG(0) we can go ahead and + * do DEPXFERCFG for every hardware endpoint as well. We are + * guaranteed that there are as many transfer resources as endpoints. + * + * This function is called for each endpoint when it is being enabled + * but is triggered only when called for EP0-out, which always happens + * first, and which should only happen in one of the above conditions. + */ static int dwc3_gadget_start_config(struct dwc3 *dwc, struct dwc3_ep *dep) { struct dwc3_gadget_ep_cmd_params params; u32 cmd; + int i; + int ret; + + if (dep->number) + return 0; memset(¶ms, 0x00, sizeof(params)); + cmd = DWC3_DEPCMD_DEPSTARTCFG; - if (dep->number != 1) { - cmd = DWC3_DEPCMD_DEPSTARTCFG; - /* XferRscIdx == 0 for ep0 and 2 for the remaining */ - if (dep->number > 1) { - if (dwc->start_config_issued) - return 0; - dwc->start_config_issued = true; - cmd |= DWC3_DEPCMD_PARAM(2); - } + ret = dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + if (ret) + return ret; - return dwc3_send_gadget_ep_cmd(dwc, 0, cmd, ¶ms); + for (i = 0; i < DWC3_ENDPOINTS_NUM; i++) { + struct dwc3_ep *dep = dwc->eps[i]; + + if (!dep) + continue; + + ret = dwc3_gadget_set_xfer_resource(dwc, dep); + if (ret) + return ret; } return 0; @@ -516,10 +558,6 @@ static int __dwc3_gadget_ep_enable(struct dwc3_ep *dep, struct dwc3_trb *trb_st_hw; struct dwc3_trb *trb_link; - ret = dwc3_gadget_set_xfer_resource(dwc, dep); - if (ret) - return ret; - dep->endpoint.desc = desc; dep->comp_desc = comp_desc; dep->type = usb_endpoint_type(desc); @@ -1636,8 +1674,6 @@ static int dwc3_gadget_start(struct usb_gadget *g, } dwc3_writel(dwc->regs, DWC3_DCFG, reg); - dwc->start_config_issued = false; - /* Start with SuperSpeed Default */ dwc3_gadget_ep0_desc.wMaxPacketSize = cpu_to_le16(512); @@ -2237,7 +2273,6 @@ static void dwc3_gadget_disconnect_interrupt(struct dwc3 *dwc) dwc3_writel(dwc->regs, DWC3_DCTL, reg); dwc3_disconnect_gadget(dwc); - dwc->start_config_issued = false; dwc->gadget.speed = USB_SPEED_UNKNOWN; dwc->setup_packet_pending = false; @@ -2288,7 +2323,6 @@ static void dwc3_gadget_reset_interrupt(struct dwc3 *dwc) dwc3_stop_active_transfers(dwc); dwc3_clear_stall_all_ep(dwc); - dwc->start_config_issued = false; /* Reset device address to zero */ reg = dwc3_readl(dwc->regs, DWC3_DCFG); From 3142a16b9816c24501103a92010a283eb6e2766c Mon Sep 17 00:00:00 2001 From: Vardan Mikayelyan Date: Tue, 16 Feb 2016 15:01:53 -0800 Subject: [PATCH 238/489] usb: dwc2: host: fix logical omissions in dwc2_process_non_isoc_desc Fixes memory manipulation issues and makes Host DDMA bulk transfers work. dwc2_process_non_isoc_desc() must return non zero value ONLY when failure happens in one of the queued descriptors. After receiving non zero value the caller must stop processing of remaining QTDs and their descriptors from chain. Commit 26a19ea699060fde ("usb: dwc2: host: fix use of qtd after free in desc dma mode") breaks non_isoc transaction completion logic in Host DDMA mode. There were bugs before that, but after this patch dwc2_process_non_isoc_desc() returns fail status even if descriptor was processed normally. This causes break from loop which is processing remaining descriptors assigned to QTD, which is not correct for QTDs containing more than one descriptor. Current dwc2 driver gathers queued BULK URBs until receiving URB without URB_NO_INTERRUPT flag. Once getting it, SW creates descriptor chain, stores it in qh structure and passes start address to HW. Multiple URB data is contained in that chain. Hence on getting error on descriptor after its processing by HW, SW should go out of both loops(qh->qtd, qtd->descs) and report the failure. Fixes: 26a19ea699060fde ("usb: dwc2: host: fix use of qtd after free in desc dma mode") Cc: Gregory Herrero Signed-off-by: Vardan Mikayelyan Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/hcd_ddma.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 36606fc33c0d..89db47a1ffed 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -1174,14 +1174,11 @@ static int dwc2_process_non_isoc_desc(struct dwc2_hsotg *hsotg, failed = dwc2_update_non_isoc_urb_state_ddma(hsotg, chan, qtd, dma_desc, halt_status, n_bytes, xfer_done); - if (*xfer_done && urb->status != -EINPROGRESS) - failed = 1; - - if (failed) { + if (failed || (*xfer_done && urb->status != -EINPROGRESS)) { dwc2_host_complete(hsotg, qtd, urb->status); dwc2_hcd_qtd_unlink_and_free(hsotg, qtd, qh); - dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x status=%08x\n", - failed, *xfer_done, urb->status); + dev_vdbg(hsotg->dev, "failed=%1x xfer_done=%1x\n", + failed, *xfer_done); return failed; } @@ -1236,21 +1233,23 @@ static void dwc2_complete_non_isoc_xfer_ddma(struct dwc2_hsotg *hsotg, list_for_each_safe(qtd_item, qtd_tmp, &qh->qtd_list) { int i; + int qtd_desc_count; qtd = list_entry(qtd_item, struct dwc2_qtd, qtd_list_entry); xfer_done = 0; + qtd_desc_count = qtd->n_desc; - for (i = 0; i < qtd->n_desc; i++) { + for (i = 0; i < qtd_desc_count; i++) { if (dwc2_process_non_isoc_desc(hsotg, chan, chnum, qtd, desc_num, halt_status, - &xfer_done)) { - qtd = NULL; - break; - } + &xfer_done)) + goto stop_scan; + desc_num++; } } +stop_scan: if (qh->ep_type != USB_ENDPOINT_XFER_CONTROL) { /* * Resetting the data toggle for bulk and interrupt endpoints From 62943b7dfa35887a40f71f698deec4488bf73036 Mon Sep 17 00:00:00 2001 From: "Tang, Jianqiang" Date: Tue, 16 Feb 2016 15:02:07 -0800 Subject: [PATCH 239/489] usb: dwc2: host: fix the data toggle error in full speed descriptor dma There will be data toggle error happen for full speed buld-out transfer. The data toggle bit is saved in qh for non-control transfers, it is wrong to check the qtd for that case. Also fix one static analysis tool issue after fix the data toggle error. John Youn: * Added WARN() to warn on improper usage of the dwc2_hcd_save_data_toggle() function. Signed-off-by: Dyson Lee Signed-off-by: Tang, Jianqiang Signed-off-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/hcd_ddma.c | 2 +- drivers/usb/dwc2/hcd_intr.c | 8 ++++++++ 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/drivers/usb/dwc2/hcd_ddma.c b/drivers/usb/dwc2/hcd_ddma.c index 89db47a1ffed..a41274aa52ad 100644 --- a/drivers/usb/dwc2/hcd_ddma.c +++ b/drivers/usb/dwc2/hcd_ddma.c @@ -1257,7 +1257,7 @@ stop_scan: */ if (halt_status == DWC2_HC_XFER_STALL) qh->data_toggle = DWC2_HC_PID_DATA0; - else if (qtd) + else dwc2_hcd_save_data_toggle(hsotg, chan, chnum, qtd); } diff --git a/drivers/usb/dwc2/hcd_intr.c b/drivers/usb/dwc2/hcd_intr.c index f8253803a050..cadba8b13c48 100644 --- a/drivers/usb/dwc2/hcd_intr.c +++ b/drivers/usb/dwc2/hcd_intr.c @@ -525,11 +525,19 @@ void dwc2_hcd_save_data_toggle(struct dwc2_hsotg *hsotg, u32 pid = (hctsiz & TSIZ_SC_MC_PID_MASK) >> TSIZ_SC_MC_PID_SHIFT; if (chan->ep_type != USB_ENDPOINT_XFER_CONTROL) { + if (WARN(!chan || !chan->qh, + "chan->qh must be specified for non-control eps\n")) + return; + if (pid == TSIZ_SC_MC_PID_DATA0) chan->qh->data_toggle = DWC2_HC_PID_DATA0; else chan->qh->data_toggle = DWC2_HC_PID_DATA1; } else { + if (WARN(!qtd, + "qtd must be specified for control eps\n")) + return; + if (pid == TSIZ_SC_MC_PID_DATA0) qtd->data_toggle = DWC2_HC_PID_DATA0; else From ee89b641a9ddca5f2d1e38d205473c4b0d26c670 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 16 Feb 2016 16:10:59 +0100 Subject: [PATCH 240/489] usb: dwc2: USB_DWC2 should depend on HAS_DMA If NO_DMA=y: ERROR: "usb_gadget_map_request" [drivers/usb/dwc2/dwc2.ko] undefined! ERROR: "usb_gadget_unmap_request" [drivers/usb/dwc2/dwc2.ko] undefined! ERROR: "bad_dma_ops" [drivers/usb/dwc2/dwc2.ko] undefined! Add a dependency on HAS_DMA to fix this. Signed-off-by: Geert Uytterhoeven Acked-by: John Youn Signed-off-by: Felipe Balbi --- drivers/usb/dwc2/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/usb/dwc2/Kconfig b/drivers/usb/dwc2/Kconfig index fd95ba6ec317..f0decc0d69b5 100644 --- a/drivers/usb/dwc2/Kconfig +++ b/drivers/usb/dwc2/Kconfig @@ -1,5 +1,6 @@ config USB_DWC2 tristate "DesignWare USB2 DRD Core Support" + depends on HAS_DMA depends on USB || USB_GADGET help Say Y here if your system has a Dual Role Hi-Speed USB From 4e7f9df25874cedbbc604a5c5c2e7a6efe662387 Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Thu, 11 Feb 2016 01:05:01 +0200 Subject: [PATCH 241/489] hpet: Drop stale URLs Looks like the HPET spec at intel.com got moved. It isn't hard to find so drop the link, just mention the revision assumed. Suggested-by: Thomas Gleixner Signed-off-by: Michael S. Tsirkin Acked-by: Greg Kroah-Hartman Cc: Arnd Bergmann Cc: Clemens Ladisch Cc: Jonathan Corbet Cc: Linus Torvalds Cc: Peter Zijlstra Cc: linux-doc@vger.kernel.org Link: http://lkml.kernel.org/r/1455145462-3877-1-git-send-email-mst@redhat.com Signed-off-by: Ingo Molnar --- Documentation/timers/hpet.txt | 4 +--- arch/x86/Kconfig | 4 ++-- drivers/char/hpet.c | 2 +- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/Documentation/timers/hpet.txt b/Documentation/timers/hpet.txt index 767392ffd31e..a484d2c109d7 100644 --- a/Documentation/timers/hpet.txt +++ b/Documentation/timers/hpet.txt @@ -1,9 +1,7 @@ High Precision Event Timer Driver for Linux The High Precision Event Timer (HPET) hardware follows a specification -by Intel and Microsoft which can be found at - - http://www.intel.com/hardwaredesign/hpetspec_1.pdf +by Intel and Microsoft, revision 1. Each HPET has one fixed-rate counter (at 10+ MHz, hence "High Precision") and up to 32 comparators. Normally three or more comparators are provided, diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ab2ed5328f0a..c46662f64c39 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -778,8 +778,8 @@ config HPET_TIMER HPET is the next generation timer replacing legacy 8254s. The HPET provides a stable time base on SMP systems, unlike the TSC, but it is more expensive to access, - as it is off-chip. You can find the HPET spec at - . + as it is off-chip. The interface used is documented + in the HPET spec, revision 1. You can safely choose Y here. However, HPET will only be activated if the platform and the BIOS support this feature. diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index 240b6cf1d97c..be54e5331a45 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -42,7 +42,7 @@ /* * The High Precision Event Timer driver. * This driver is closely modelled after the rtc.c driver. - * http://www.intel.com/hardwaredesign/hpetspec_1.pdf + * See HPET spec revision 1. */ #define HPET_USER_FREQ (64) #define HPET_DRIFT (500) From c219b7ddb6a3524a61a89438d86e4a8639706308 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 10 Feb 2016 12:04:22 -0500 Subject: [PATCH 242/489] sched/deadline: Fix trivial typo in printk() message It's "too much" not "to much". Signed-off-by: Steven Rostedt Acked-by: Juri Lelli Cc: Jiri Kosina Cc: Juri Lelli Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20160210120422.4ca77e68@gandalf.local.home Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index cd64c979d0e1..57b939c81bce 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -420,7 +420,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * entity. */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { - printk_deferred_once("sched: DL replenish lagged to much\n"); + printk_deferred_once("sched: DL replenish lagged too much\n"); dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } From d2613f56ce0287211d70a86443a143cae1887911 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 28 Jan 2016 16:04:21 +0100 Subject: [PATCH 243/489] ARM: shmobile: Move shmobile_scu_base from .text to .bss shmobile_scu_base is being written to, so it doesn't belong in the .text section. Fix this by moving it from asm .text to C .bss, as it's no longer used from asm code since commit 4f6da36f7edd5790 ("ARM: shmobile: Remove old SCU boot code"). Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/headsmp-scu.S | 6 ------ arch/arm/mach-shmobile/platsmp-scu.c | 3 +++ 2 files changed, 3 insertions(+), 6 deletions(-) diff --git a/arch/arm/mach-shmobile/headsmp-scu.S b/arch/arm/mach-shmobile/headsmp-scu.S index fa5248c52399..5e503d91ad70 100644 --- a/arch/arm/mach-shmobile/headsmp-scu.S +++ b/arch/arm/mach-shmobile/headsmp-scu.S @@ -38,9 +38,3 @@ ENTRY(shmobile_boot_scu) b secondary_startup ENDPROC(shmobile_boot_scu) - - .text - .align 2 - .globl shmobile_scu_base -shmobile_scu_base: - .space 4 diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c index 64663110ab6c..f2198c9c7435 100644 --- a/arch/arm/mach-shmobile/platsmp-scu.c +++ b/arch/arm/mach-shmobile/platsmp-scu.c @@ -17,6 +17,9 @@ #include #include "common.h" + +void __iomem *shmobile_scu_base; + static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { From b1568d80123a7e7ab528f587ef6896b2d5413b61 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Thu, 28 Jan 2016 16:13:31 +0100 Subject: [PATCH 244/489] ARM: shmobile: r8a7779: Remove remainings of removed SCU boot setup code Commit 0ca2894b5a900709 ("ARM: shmobile: Use shared SCU SMP boot code on r8a7779") obsoleted the r8a7779-specific SCU boot code, but forgot to remove the setup of shmobile_boot_fn and shmobile_boot_arg, which is overwritten by shmobile_smp_scu_prepare_cpus(). Note that shmobile_scu_base wasn't initialized at that point yet anyway. Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/smp-r8a7779.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/arm/mach-shmobile/smp-r8a7779.c b/arch/arm/mach-shmobile/smp-r8a7779.c index b854fe2095ad..0b024a9dbd43 100644 --- a/arch/arm/mach-shmobile/smp-r8a7779.c +++ b/arch/arm/mach-shmobile/smp-r8a7779.c @@ -92,8 +92,6 @@ static void __init r8a7779_smp_prepare_cpus(unsigned int max_cpus) { /* Map the reset vector (in headsmp-scu.S, headsmp.S) */ __raw_writel(__pa(shmobile_boot_vector), AVECR); - shmobile_boot_fn = virt_to_phys(shmobile_boot_scu); - shmobile_boot_arg = (unsigned long)shmobile_scu_base; /* setup r8a7779 specific SCU bits */ shmobile_scu_base = IOMEM(R8A7779_SCU_BASE); From 4e960f52fce16a3bf3261fa92c34cf2306059ba2 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 15 Feb 2016 13:20:07 +0100 Subject: [PATCH 245/489] ARM: shmobile: Move shmobile_smp_{mpidr, fn, arg}[] from .text to .bss If CONFIG_DEBUG_RODATA=y, the kernel crashes during system suspend: Freezing user space processes ... (elapsed 0.004 seconds) done. Freezing remaining freezable tasks ... (elapsed 0.002 seconds) done. PM: suspend of devices complete after 111.948 msecs PM: late suspend of devices complete after 1.086 msecs PM: noirq suspend of devices complete after 11.576 msecs Disabling non-boot CPUs ... Kernel panic - not syncing: Attempted to kill the idle task! 1014ec ---[ end Kernel panic - not syncing: Attempted to kill the idle task! CPU0: stopping This happens because the .text section is marked read-only, while the arrays shmobile_smp_mpidr[], shmobile_smp_fn[], and shmobile_smp_arg[] are being written to. Fix this by moving these arrays from the .text to the .bss section. This requires accessing them through PC-relative offsets. Signed-off-by: Geert Uytterhoeven Reviewed-by: Kees Cook Reviewed-by: Nicolas Pitre Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/headsmp.S | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S index 330c1fc63197..94d86ed16414 100644 --- a/arch/arm/mach-shmobile/headsmp.S +++ b/arch/arm/mach-shmobile/headsmp.S @@ -50,9 +50,11 @@ ENTRY(shmobile_smp_boot) mrc p15, 0, r1, c0, c0, 5 @ r1 = MPIDR and r0, r1, r0 @ r0 = cpu_logical_map() value mov r1, #0 @ r1 = CPU index - adr r5, 1f @ array of per-cpu mpidr values - adr r6, 2f @ array of per-cpu functions - adr r7, 3f @ array of per-cpu arguments + adr r2, 1f + ldmia r2, {r5, r6, r7} + add r5, r5, r2 @ array of per-cpu mpidr values + add r6, r6, r2 @ array of per-cpu functions + add r7, r7, r2 @ array of per-cpu arguments shmobile_smp_boot_find_mpidr: ldr r8, [r5, r1, lsl #2] @@ -80,12 +82,18 @@ ENTRY(shmobile_smp_sleep) b shmobile_smp_boot ENDPROC(shmobile_smp_sleep) + .align 2 +1: .long shmobile_smp_mpidr - . + .long shmobile_smp_fn - 1b + .long shmobile_smp_arg - 1b + + .bss .globl shmobile_smp_mpidr shmobile_smp_mpidr: -1: .space NR_CPUS * 4 + .space NR_CPUS * 4 .globl shmobile_smp_fn shmobile_smp_fn: -2: .space NR_CPUS * 4 + .space NR_CPUS * 4 .globl shmobile_smp_arg shmobile_smp_arg: -3: .space NR_CPUS * 4 + .space NR_CPUS * 4 From 901c5ffaaed117a38be9d0c29247c4888d6c8636 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 15 Feb 2016 13:20:08 +0100 Subject: [PATCH 246/489] ARM: shmobile: Remove shmobile_boot_arg CPU boot configuration writes to shmobile_boot_arg, which is located in the .text section, and thus should not be written to. As of commit 1d33a354bbb618ba ("ARM: shmobile: Per-CPU SMP boot / sleep code for SCU SoCs"), and ignoring accidental remainings, shmobile_boot_arg is always set to MPIDR_HWID_BITMASK by C code. Hence we can just hardcode this in the assembler code, and remove the variable, and thus also remove the need to write to this variable. Signed-off-by: Geert Uytterhoeven Acked-by: Nicolas Pitre Signed-off-by: Simon Horman --- arch/arm/mach-shmobile/common.h | 1 - arch/arm/mach-shmobile/headsmp.S | 8 ++------ arch/arm/mach-shmobile/platsmp-apmu.c | 1 - arch/arm/mach-shmobile/platsmp-scu.c | 1 - 4 files changed, 2 insertions(+), 9 deletions(-) diff --git a/arch/arm/mach-shmobile/common.h b/arch/arm/mach-shmobile/common.h index 9cb11215ceba..b3a4ed5289ec 100644 --- a/arch/arm/mach-shmobile/common.h +++ b/arch/arm/mach-shmobile/common.h @@ -4,7 +4,6 @@ extern void shmobile_init_delay(void); extern void shmobile_boot_vector(void); extern unsigned long shmobile_boot_fn; -extern unsigned long shmobile_boot_arg; extern unsigned long shmobile_boot_size; extern void shmobile_smp_boot(void); extern void shmobile_smp_sleep(void); diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S index 94d86ed16414..32e0bf6e3ccb 100644 --- a/arch/arm/mach-shmobile/headsmp.S +++ b/arch/arm/mach-shmobile/headsmp.S @@ -24,7 +24,6 @@ .arm .align 12 ENTRY(shmobile_boot_vector) - ldr r0, 2f ldr r1, 1f bx r1 @@ -34,9 +33,6 @@ ENDPROC(shmobile_boot_vector) .globl shmobile_boot_fn shmobile_boot_fn: 1: .space 4 - .globl shmobile_boot_arg -shmobile_boot_arg: -2: .space 4 .globl shmobile_boot_size shmobile_boot_size: .long . - shmobile_boot_vector @@ -46,9 +42,9 @@ shmobile_boot_size: */ ENTRY(shmobile_smp_boot) - @ r0 = MPIDR_HWID_BITMASK mrc p15, 0, r1, c0, c0, 5 @ r1 = MPIDR - and r0, r1, r0 @ r0 = cpu_logical_map() value + and r0, r1, #0xffffff @ MPIDR_HWID_BITMASK + @ r0 = cpu_logical_map() value mov r1, #0 @ r1 = CPU index adr r2, 1f ldmia r2, {r5, r6, r7} diff --git a/arch/arm/mach-shmobile/platsmp-apmu.c b/arch/arm/mach-shmobile/platsmp-apmu.c index 911884f7e28b..aba75c89f9c1 100644 --- a/arch/arm/mach-shmobile/platsmp-apmu.c +++ b/arch/arm/mach-shmobile/platsmp-apmu.c @@ -123,7 +123,6 @@ void __init shmobile_smp_apmu_prepare_cpus(unsigned int max_cpus, { /* install boot code shared by all CPUs */ shmobile_boot_fn = virt_to_phys(shmobile_smp_boot); - shmobile_boot_arg = MPIDR_HWID_BITMASK; /* perform per-cpu setup */ apmu_parse_cfg(apmu_init_cpu, apmu_config, num); diff --git a/arch/arm/mach-shmobile/platsmp-scu.c b/arch/arm/mach-shmobile/platsmp-scu.c index f2198c9c7435..081a097c9219 100644 --- a/arch/arm/mach-shmobile/platsmp-scu.c +++ b/arch/arm/mach-shmobile/platsmp-scu.c @@ -44,7 +44,6 @@ void __init shmobile_smp_scu_prepare_cpus(unsigned int max_cpus) { /* install boot code shared by all CPUs */ shmobile_boot_fn = virt_to_phys(shmobile_smp_boot); - shmobile_boot_arg = MPIDR_HWID_BITMASK; /* enable SCU and cache coherency on booting CPU */ scu_enable(shmobile_scu_base); From 8d409cb3e8a24196be7271defafd4638f3e0b514 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= Date: Wed, 10 Feb 2016 19:59:05 +0200 Subject: [PATCH 247/489] drm/i915: Fix hpd live status bits for g4x MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Looks like g4x hpd live status bits actually agree with the spec. At least they do on the machine I have, and apparently on Nick Bowler's g4x as well. So gm45 may be the only platform where they don't agree. At least that seems to be the case based on the (somewhat incomplete) logs/dumps in [1], and Daniel has also tested this on his gm45 sometime in the past. So let's change the bits to match the spec on g4x. That actually makes the g4x bits identical to vlv/chv so we can just share the code between those platforms, leaving gm45 as the special case. [1] https://bugzilla.kernel.org/show_bug.cgi?id=52361 Cc: Shashank Sharma Cc: Sonika Jindal Cc: Daniel Vetter Cc: Jani Nikula Cc: Nick Bowler References: https://lists.freedesktop.org/archives/dri-devel/2016-February/100382.html Reported-by: Nick Bowler Cc: stable@vger.kernel.org Fixes: 237ed86c693d ("drm/i915: Check live status before reading edid") Signed-off-by: Ville Syrjälä Link: http://patchwork.freedesktop.org/patch/msgid/1455127145-20087-1-git-send-email-ville.syrjala@linux.intel.com Reviewed-by: Daniel Vetter (cherry picked from commit 0780cd36c7af70c55981ee624084f0f48cae9b95) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_reg.h | 15 ++++++++------- drivers/gpu/drm/i915/intel_dp.c | 14 +++++++------- 2 files changed, 15 insertions(+), 14 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index b9a564b76528..4897728713f6 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -3287,19 +3287,20 @@ enum skl_disp_power_wells { #define PORT_HOTPLUG_STAT _MMIO(dev_priv->info.display_mmio_offset + 0x61114) /* - * HDMI/DP bits are gen4+ + * HDMI/DP bits are g4x+ * * WARNING: Bspec for hpd status bits on gen4 seems to be completely confused. * Please check the detailed lore in the commit message for for experimental * evidence. */ -#define PORTD_HOTPLUG_LIVE_STATUS_G4X (1 << 29) +/* Bspec says GM45 should match G4X/VLV/CHV, but reality disagrees */ +#define PORTD_HOTPLUG_LIVE_STATUS_GM45 (1 << 29) +#define PORTC_HOTPLUG_LIVE_STATUS_GM45 (1 << 28) +#define PORTB_HOTPLUG_LIVE_STATUS_GM45 (1 << 27) +/* G4X/VLV/CHV DP/HDMI bits again match Bspec */ +#define PORTD_HOTPLUG_LIVE_STATUS_G4X (1 << 27) #define PORTC_HOTPLUG_LIVE_STATUS_G4X (1 << 28) -#define PORTB_HOTPLUG_LIVE_STATUS_G4X (1 << 27) -/* VLV DP/HDMI bits again match Bspec */ -#define PORTD_HOTPLUG_LIVE_STATUS_VLV (1 << 27) -#define PORTC_HOTPLUG_LIVE_STATUS_VLV (1 << 28) -#define PORTB_HOTPLUG_LIVE_STATUS_VLV (1 << 29) +#define PORTB_HOTPLUG_LIVE_STATUS_G4X (1 << 29) #define PORTD_HOTPLUG_INT_STATUS (3 << 21) #define PORTD_HOTPLUG_INT_LONG_PULSE (2 << 21) #define PORTD_HOTPLUG_INT_SHORT_PULSE (1 << 21) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 796e3d313cb9..1bbd67b046da 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -4493,20 +4493,20 @@ static bool g4x_digital_port_connected(struct drm_i915_private *dev_priv, return I915_READ(PORT_HOTPLUG_STAT) & bit; } -static bool vlv_digital_port_connected(struct drm_i915_private *dev_priv, - struct intel_digital_port *port) +static bool gm45_digital_port_connected(struct drm_i915_private *dev_priv, + struct intel_digital_port *port) { u32 bit; switch (port->port) { case PORT_B: - bit = PORTB_HOTPLUG_LIVE_STATUS_VLV; + bit = PORTB_HOTPLUG_LIVE_STATUS_GM45; break; case PORT_C: - bit = PORTC_HOTPLUG_LIVE_STATUS_VLV; + bit = PORTC_HOTPLUG_LIVE_STATUS_GM45; break; case PORT_D: - bit = PORTD_HOTPLUG_LIVE_STATUS_VLV; + bit = PORTD_HOTPLUG_LIVE_STATUS_GM45; break; default: MISSING_CASE(port->port); @@ -4558,8 +4558,8 @@ bool intel_digital_port_connected(struct drm_i915_private *dev_priv, return cpt_digital_port_connected(dev_priv, port); else if (IS_BROXTON(dev_priv)) return bxt_digital_port_connected(dev_priv, port); - else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) - return vlv_digital_port_connected(dev_priv, port); + else if (IS_GM45(dev_priv)) + return gm45_digital_port_connected(dev_priv, port); else return g4x_digital_port_connected(dev_priv, port); } From 722ec35f7faefcc34d12616eca7976a848870f9d Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Tue, 16 Feb 2016 15:14:44 +0100 Subject: [PATCH 248/489] arm64: dma-mapping: fix handling of devices registered before arch_initcall This patch ensures that devices, which got registered before arch_initcall will be handled correctly by IOMMU-based DMA-mapping code. Cc: Fixes: 13b8629f6511 ("arm64: Add IOMMU dma_ops") Acked-by: Robin Murphy Signed-off-by: Marek Szyprowski Signed-off-by: Will Deacon --- arch/arm64/mm/dma-mapping.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 331c4ca6205c..a6e757cbab77 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -933,6 +933,10 @@ static int __init __iommu_dma_init(void) ret = register_iommu_dma_ops_notifier(&platform_bus_type); if (!ret) ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); return ret; } arch_initcall(__iommu_dma_init); From 6ecad912a0073c768db1491c27ca55ad2d0ee68f Mon Sep 17 00:00:00 2001 From: Alexey Kardashevskiy Date: Wed, 17 Feb 2016 18:26:31 +1100 Subject: [PATCH 249/489] powerpc/ioda: Set "read" permission when "write" is set Quite often drivers set only "write" permission assuming that this includes "read" permission as well and this works on plenty of platforms. However IODA2 is strict about this and produces an EEH when "read" permission is not set and reading happens. This adds a workaround in the IODA code to always add the "read" bit when the "write" bit is set. Fixes: 10b35b2b7485 ("powerpc/powernv: Do not set "read" flag if direction==DMA_NONE") Cc: stable@vger.kernel.org # 4.2+ Cc: Benjamin Herrenschmidt Signed-off-by: Alexey Kardashevskiy Tested-by: Douglas Miller Signed-off-by: Michael Ellerman --- arch/powerpc/platforms/powernv/pci.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c index d25ff2292ae2..b1ef84a6c9d1 100644 --- a/arch/powerpc/platforms/powernv/pci.c +++ b/arch/powerpc/platforms/powernv/pci.c @@ -599,6 +599,9 @@ int pnv_tce_build(struct iommu_table *tbl, long index, long npages, u64 rpn = __pa(uaddr) >> tbl->it_page_shift; long i; + if (proto_tce & TCE_PCI_WRITE) + proto_tce |= TCE_PCI_READ; + for (i = 0; i < npages; i++) { unsigned long newtce = proto_tce | ((rpn + i) << tbl->it_page_shift); @@ -620,6 +623,9 @@ int pnv_tce_xchg(struct iommu_table *tbl, long index, BUG_ON(*hpa & ~IOMMU_PAGE_MASK(tbl)); + if (newtce & TCE_PCI_WRITE) + newtce |= TCE_PCI_READ; + oldtce = xchg(pnv_tce(tbl, idx), cpu_to_be64(newtce)); *hpa = be64_to_cpu(oldtce) & ~(TCE_PCI_READ | TCE_PCI_WRITE); *direction = iommu_tce_direction(oldtce); From 96c7de4ff41c2ed6da43141a4deb922de09617d0 Mon Sep 17 00:00:00 2001 From: Andrzej Hajda Date: Mon, 15 Feb 2016 15:35:25 +0100 Subject: [PATCH 250/489] usb: gadget: fsl_qe_udc: fix IS_ERR_VALUE usage IS_ERR_VALUE macro should be used only with unsigned long type. Otherwise it can work incorrectly. The patch follows conclusion from discussion on LKML [1][2]. [1]: http://permalink.gmane.org/gmane.linux.kernel/2120927 [2]: http://permalink.gmane.org/gmane.linux.kernel/2150581 Signed-off-by: Andrzej Hajda Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/fsl_qe_udc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/fsl_qe_udc.c b/drivers/usb/gadget/udc/fsl_qe_udc.c index 53c0692f1b09..93d28cb00b76 100644 --- a/drivers/usb/gadget/udc/fsl_qe_udc.c +++ b/drivers/usb/gadget/udc/fsl_qe_udc.c @@ -2340,7 +2340,7 @@ static struct qe_udc *qe_udc_config(struct platform_device *ofdev) { struct qe_udc *udc; struct device_node *np = ofdev->dev.of_node; - unsigned int tmp_addr = 0; + unsigned long tmp_addr = 0; struct usb_device_para __iomem *usbpram; unsigned int i; u64 size; From bba40e6948b94cba71965285fbac31bd078c024a Mon Sep 17 00:00:00 2001 From: Cristian Birsan Date: Thu, 11 Feb 2016 08:58:17 -0700 Subject: [PATCH 251/489] usb: musb: Fix DMA desired mode for Mentor DMA engine Commit 754fe4a92c07 ("usb: musb: Remove ifdefs for TX DMA for musb_host.c") introduces a problem setting the desired channel mode for the Mentor DMA engine. There is a case where an address is incorrectly assigned to the DMA channel desired mode when it should instead be assigned the actual mode value. This results in the value of channel->desired_mode not being correct. Acked-by: Sergei Shtylyov Signed-off-by: Cristian Birsan Signed-off-by: Joshua Henderson Signed-off-by: Felipe Balbi --- drivers/usb/musb/musb_host.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 795a45b1b25b..79d081883628 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -662,7 +662,7 @@ static int musb_tx_dma_set_mode_mentor(struct dma_controller *dma, csr &= ~(MUSB_TXCSR_AUTOSET | MUSB_TXCSR_DMAMODE); csr |= MUSB_TXCSR_DMAENAB; /* against programmer's guide */ } - channel->desired_mode = mode; + channel->desired_mode = *mode; musb_writew(epio, MUSB_TXCSR, csr); return 0; From b41f7852f3b981df30727f5cd64c1877ceee794e Mon Sep 17 00:00:00 2001 From: Devesh Sharma Date: Thu, 11 Feb 2016 00:21:52 -0500 Subject: [PATCH 252/489] RDMA/ocrdma: Fix arm logic to align with new cq API Today ocrdma driver defer arming the CQ till poll is called. This was used to prevent calling poll-cq on an armed CQ. Recently a set of new CQ API has been introduced into the linux kernel. The implementation of this API guarantees that a given CQ is never armed before calling poll on it. Most of the kernel ULPs have already moved to use this new API or have a code where poll is called before arming the CQ. Thus, the above workaround in ocrdma is not needed anymore. This patch removes the additional logic to deffer arm till poll is called. This patch adds a simple scheme where ib_req_notify_cq() will actually arm the cq. Signed-off-by: Devesh Sharma Signed-off-by: Doug Ledford --- drivers/infiniband/hw/ocrdma/ocrdma.h | 3 --- drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 18 ++++-------------- 2 files changed, 4 insertions(+), 17 deletions(-) diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h index 040bb8b5cb15..12503f15fbd6 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma.h +++ b/drivers/infiniband/hw/ocrdma/ocrdma.h @@ -323,9 +323,6 @@ struct ocrdma_cq { */ u32 max_hw_cqe; bool phase_change; - bool deferred_arm, deferred_sol; - bool first_arm; - spinlock_t cq_lock ____cacheline_aligned; /* provide synchronization * to cq polling */ diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c index 37620b4baafb..12420e4ecf3d 100644 --- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c +++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c @@ -1094,7 +1094,6 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, spin_lock_init(&cq->comp_handler_lock); INIT_LIST_HEAD(&cq->sq_head); INIT_LIST_HEAD(&cq->rq_head); - cq->first_arm = true; if (ib_ctx) { uctx = get_ocrdma_ucontext(ib_ctx); @@ -2910,12 +2909,9 @@ expand_cqe: } stop_cqe: cq->getp = cur_getp; - if (cq->deferred_arm || polled_hw_cqes) { - ocrdma_ring_cq_db(dev, cq->id, cq->deferred_arm, - cq->deferred_sol, polled_hw_cqes); - cq->deferred_arm = false; - cq->deferred_sol = false; - } + + if (polled_hw_cqes) + ocrdma_ring_cq_db(dev, cq->id, false, false, polled_hw_cqes); return i; } @@ -2999,13 +2995,7 @@ int ocrdma_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags cq_flags) if (cq_flags & IB_CQ_SOLICITED) sol_needed = true; - if (cq->first_arm) { - ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0); - cq->first_arm = false; - } - - cq->deferred_arm = true; - cq->deferred_sol = sol_needed; + ocrdma_ring_cq_db(dev, cq_id, arm_needed, sol_needed, 0); spin_unlock_irqrestore(&cq->cq_lock, flags); return 0; From c3c0c83667a9fe78cc28c27ec9e5ace3411ae775 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 11 Feb 2016 10:24:43 +0200 Subject: [PATCH 253/489] IB/mlx4: Add support for extended counters over RoCE ports When attribute IB_PMA_PORT_COUNTERS_EXT is set, we now return 64 bit values for the counters. Signed-off-by: Eran Ben Elisha Signed-off-by: Matan Barak Reviewed-by: Or Gerlitz Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx4/mad.c | 50 +++++++++++++++++++++++--------- 1 file changed, 37 insertions(+), 13 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 26833bfa639b..75cbe1edc1e7 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -817,17 +817,39 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; } -static void edit_counter(struct mlx4_counter *cnt, - struct ib_pma_portcounters *pma_cnt) +static void edit_counter(struct mlx4_counter *cnt, void *counters, + __be16 attr_id) { - ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data, - (be64_to_cpu(cnt->tx_bytes) >> 2)); - ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data, - (be64_to_cpu(cnt->rx_bytes) >> 2)); - ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets, - be64_to_cpu(cnt->tx_frames)); - ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets, - be64_to_cpu(cnt->rx_frames)); + switch (attr_id) { + case IB_PMA_PORT_COUNTERS: + { + struct ib_pma_portcounters *pma_cnt = + (struct ib_pma_portcounters *)counters; + + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_data, + (be64_to_cpu(cnt->tx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_data, + (be64_to_cpu(cnt->rx_bytes) >> 2)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_xmit_packets, + be64_to_cpu(cnt->tx_frames)); + ASSIGN_32BIT_COUNTER(pma_cnt->port_rcv_packets, + be64_to_cpu(cnt->rx_frames)); + break; + } + case IB_PMA_PORT_COUNTERS_EXT: + { + struct ib_pma_portcounters_ext *pma_cnt_ext = + (struct ib_pma_portcounters_ext *)counters; + + pma_cnt_ext->port_xmit_data = + cpu_to_be64(be64_to_cpu(cnt->tx_bytes) >> 2); + pma_cnt_ext->port_rcv_data = + cpu_to_be64(be64_to_cpu(cnt->rx_bytes) >> 2); + pma_cnt_ext->port_xmit_packets = cnt->tx_frames; + pma_cnt_ext->port_rcv_packets = cnt->rx_frames; + break; + } + } } static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, @@ -863,7 +885,8 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, switch (counter_stats.counter_mode & 0xf) { case 0: edit_counter(&counter_stats, - (void *)(out_mad->data + 40)); + (void *)(out_mad->data + 40), + in_mad->mad_hdr.attr_id); err = IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; break; default: @@ -894,8 +917,9 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, */ if (link == IB_LINK_LAYER_INFINIBAND) { if (mlx4_is_slave(dev->dev) && - in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT && - in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS) + (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT && + (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS || + in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT))) return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, in_grh, in_mad, out_mad); From c2bab619813a525d3f58b5ffbfcdc4edee27e497 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Thu, 11 Feb 2016 10:24:44 +0200 Subject: [PATCH 254/489] IB/mlx4: Add support for the port info class for RoCE ports Report that driver supports IB_PMA_CLASS_CAP_EXT_WIDTH in respond for IB_MGMT_CLASS_PERF_MGMT mad with IB_PMA_CLASS_PORT_INFO attr id. Signed-off-by: Eran Ben Elisha Signed-off-by: Matan Barak Reviewed-by: Or Gerlitz Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx4/mad.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c index 75cbe1edc1e7..d68f506c1922 100644 --- a/drivers/infiniband/hw/mlx4/mad.c +++ b/drivers/infiniband/hw/mlx4/mad.c @@ -852,6 +852,15 @@ static void edit_counter(struct mlx4_counter *cnt, void *counters, } } +static int iboe_process_mad_port_info(void *out_mad) +{ + struct ib_class_port_info cpi = {}; + + cpi.capability_mask = IB_PMA_CLASS_CAP_EXT_WIDTH; + memcpy(out_mad, &cpi, sizeof(cpi)); + return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY; +} + static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad *in_mad, struct ib_mad *out_mad) @@ -864,6 +873,9 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, if (in_mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_PERF_MGMT) return -EINVAL; + if (in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO) + return iboe_process_mad_port_info((void *)(out_mad->data + 40)); + memset(&counter_stats, 0, sizeof(counter_stats)); mutex_lock(&dev->counters_table[port_num - 1].mutex); list_for_each_entry(tmp_counter, @@ -919,7 +931,8 @@ int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, if (mlx4_is_slave(dev->dev) && (in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT && (in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS || - in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT))) + in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS_EXT || + in_mad->mad_hdr.attr_id == IB_PMA_CLASS_PORT_INFO))) return iboe_process_mad(ibdev, mad_flags, port_num, in_wc, in_grh, in_mad, out_mad); From 9f74660bcf1e4cca577be99e54bc77b5df62b508 Mon Sep 17 00:00:00 2001 From: Chuck Lever Date: Mon, 15 Feb 2016 10:23:59 -0500 Subject: [PATCH 255/489] xprtrdma: rpcrdma_bc_receive_call() should init rq_private_buf.len Some NFSv4.1 OPEN requests were hanging waiting for the NFS server to finish recalling delegations. Turns out that each NFSv4.1 CB request on RDMA gets a GARBAGE_ARGS reply from the Linux client. Commit 756b9b37cfb2e3dc added a line in bc_svc_process that overwrites the incoming rq_rcv_buf's length with the value in rq_private_buf.len. But rpcrdma_bc_receive_call() does not invoke xprt_complete_bc_request(), thus rq_private_buf.len is not initialized. svc_process_common() is invoked with a zero-length RPC message, and fails. Fixes: 756b9b37cfb2e3dc ('SUNRPC: Fix callback channel') Signed-off-by: Chuck Lever Signed-off-by: Anna Schumaker --- net/sunrpc/xprtrdma/backchannel.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index cc1251d07297..2dcd7640eeb5 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -341,6 +341,8 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, rqst->rq_reply_bytes_recvd = 0; rqst->rq_bytes_sent = 0; rqst->rq_xid = headerp->rm_xid; + + rqst->rq_private_buf.len = size; set_bit(RPC_BC_PA_IN_USE, &rqst->rq_bc_pa_state); buf = &rqst->rq_rcv_buf; From 281e8b2fdf8e4ef366b899453cae50e09b577ada Mon Sep 17 00:00:00 2001 From: Amir Vadai Date: Wed, 17 Feb 2016 17:24:22 +0200 Subject: [PATCH 256/489] net/mlx4_en: Count HW buffer overrun only once RdropOvflw counts overrun of HW buffer, therefore should be used for rx_fifo_errors only. Currently RdropOvflw counter is mistakenly also set into rx_missed_errors and rx_over_errors too, which makes the device total dropped packets accounting to show wrong results. Fix that. Use it for rx_fifo_errors only. Fixes: c27a02cd94d6 ('mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC') Signed-off-by: Amir Vadai Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_port.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c index ee99e67187f5..3904b5fc0b7c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_port.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c @@ -238,11 +238,11 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset) stats->collisions = 0; stats->rx_dropped = be32_to_cpu(mlx4_en_stats->RDROP); stats->rx_length_errors = be32_to_cpu(mlx4_en_stats->RdropLength); - stats->rx_over_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_over_errors = 0; stats->rx_crc_errors = be32_to_cpu(mlx4_en_stats->RCRC); stats->rx_frame_errors = 0; stats->rx_fifo_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); - stats->rx_missed_errors = be32_to_cpu(mlx4_en_stats->RdropOvflw); + stats->rx_missed_errors = 0; stats->tx_aborted_errors = 0; stats->tx_carrier_errors = 0; stats->tx_fifo_errors = 0; From 31c128b66e5b28f468076e4f3ca3025c35342041 Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Wed, 17 Feb 2016 17:24:23 +0200 Subject: [PATCH 257/489] net/mlx4_en: Choose time-stamping shift value according to HW frequency Previously, the shift value used for time-stamping was constant and didn't depend on the HW chip frequency. Change that to take the frequency into account and calculate the maximal value in cycles per wraparound of ten seconds. This time slot was chosen since it gives a good accuracy in time synchronization. Algorithm for shift value calculation: * Round up the maximal value in cycles to nearest power of two * Calculate maximal multiplier by division of all 64 bits set to above result * Then, invert the function clocksource_khz2mult() to get the shift from maximal mult value Fixes: ec693d47010e ('net/mlx4_en: Add HW timestamping (TS) support') Signed-off-by: Eugenia Emantayev Reviewed-by: Matan Barak Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_clock.c | 25 ++++++++++++++----- 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c index 038f9ce391e6..1494997c4f7e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c @@ -236,6 +236,24 @@ static const struct ptp_clock_info mlx4_en_ptp_clock_info = { .enable = mlx4_en_phc_enable, }; +#define MLX4_EN_WRAP_AROUND_SEC 10ULL + +/* This function calculates the max shift that enables the user range + * of MLX4_EN_WRAP_AROUND_SEC values in the cycles register. + */ +static u32 freq_to_shift(u16 freq) +{ + u32 freq_khz = freq * 1000; + u64 max_val_cycles = freq_khz * 1000 * MLX4_EN_WRAP_AROUND_SEC; + u64 max_val_cycles_rounded = is_power_of_2(max_val_cycles + 1) ? + max_val_cycles : roundup_pow_of_two(max_val_cycles) - 1; + /* calculate max possible multiplier in order to fit in 64bit */ + u64 max_mul = div_u64(0xffffffffffffffffULL, max_val_cycles_rounded); + + /* This comes from the reverse of clocksource_khz2mult */ + return ilog2(div_u64(max_mul * freq_khz, 1000000)); +} + void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) { struct mlx4_dev *dev = mdev->dev; @@ -254,12 +272,7 @@ void mlx4_en_init_timestamp(struct mlx4_en_dev *mdev) memset(&mdev->cycles, 0, sizeof(mdev->cycles)); mdev->cycles.read = mlx4_en_read_clock; mdev->cycles.mask = CLOCKSOURCE_MASK(48); - /* Using shift to make calculation more accurate. Since current HW - * clock frequency is 427 MHz, and cycles are given using a 48 bits - * register, the biggest shift when calculating using u64, is 14 - * (max_cycles * multiplier < 2^64) - */ - mdev->cycles.shift = 14; + mdev->cycles.shift = freq_to_shift(dev->caps.hca_core_clock); mdev->cycles.mult = clocksource_khz2mult(1000 * dev->caps.hca_core_clock, mdev->cycles.shift); mdev->nominal_c_mult = mdev->cycles.mult; From 6b94bab0ee8d5def6a2aac0ef6204ee6e24386b6 Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 17 Feb 2016 17:24:24 +0200 Subject: [PATCH 258/489] net/mlx4_core: Fix potential corruption in counters database The error flow in procedure handle_existing_counter() is wrong. The procedure should exit after encountering the error, not continue as if everything is OK. Fixes: 68230242cdbc ('net/mlx4_core: Add port attribute when tracking counters') Signed-off-by: Eran Ben Elisha Signed-off-by: Jack Morgenstein Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/resource_tracker.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index b46dbe29ef6c..25ce1b030a00 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -915,11 +915,13 @@ static int handle_existing_counter(struct mlx4_dev *dev, u8 slave, int port, spin_lock_irq(mlx4_tlock(dev)); r = find_res(dev, counter_index, RES_COUNTER); - if (!r || r->owner != slave) + if (!r || r->owner != slave) { ret = -EINVAL; - counter = container_of(r, struct res_counter, com); - if (!counter->port) - counter->port = port; + } else { + counter = container_of(r, struct res_counter, com); + if (!counter->port) + counter->port = port; + } spin_unlock_irq(mlx4_tlock(dev)); return ret; From 22e3817e6c8301dc0520b855c8a2d764580e719c Mon Sep 17 00:00:00 2001 From: Daniel Jurgens Date: Wed, 17 Feb 2016 17:24:25 +0200 Subject: [PATCH 259/489] net/mlx4_core: Do not BUG_ON during reset when PCI is offline The PCI channel could go offline during reset due to EEH. Don't bug on in this case, the error is recoverable. Fixes: f6bc11e42646 ('net/mlx4_core: Enhance the catas flow to support device reset') Signed-off-by: Daniel Jurgens Reviewed-by: Yishai Hadas Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/catas.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 715de8affcc9..c7e939945259 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -182,10 +182,17 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist) err = mlx4_reset_slave(dev); else err = mlx4_reset_master(dev); - BUG_ON(err != 0); + if (!err) { + mlx4_err(dev, "device was reset successfully\n"); + } else { + /* EEH could have disabled the PCI channel during reset. That's + * recoverable and the PCI error flow will handle it. + */ + if (!pci_channel_offline(dev->persist->pdev)) + BUG_ON(1); + } dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR; - mlx4_err(dev, "device was reset successfully\n"); mutex_unlock(&persist->device_state_mutex); /* At that step HW was already reset, now notify clients */ From 85743f1eb34548ba4b056d2f184a3d107a3b8917 Mon Sep 17 00:00:00 2001 From: Huy Nguyen Date: Wed, 17 Feb 2016 17:24:26 +0200 Subject: [PATCH 260/489] net/mlx4_core: Set UAR page size to 4KB regardless of system page size problem description: The current code sets UAR page size equal to system page size. The ConnectX-3 and ConnectX-3 Pro HWs require minimum 128 UAR pages. The mlx4 kernel drivers are not loaded if there is less than 128 UAR pages. solution: Always set UAR page to 4KB. This allows more UAR pages if the OS has PAGE_SIZE larger than 4KB. For example, PowerPC kernel use 64KB system page size, with 4MB uar region, there are 4MB/2/64KB = 32 uars (half for uar, half for blueflame). This does not meet minimum 128 UAR pages requirement. With 4KB UAR page, there are 4MB/2/4KB = 512 uars which meet the minimum requirement. Note that only codes in mlx4_core that deal with firmware know that uar page size is 4KB. Codes that deal with usr page in cq and qp context (mlx4_ib, mlx4_en and part of mlx4_core) still have the same assumption that uar page size equals to system page size. Note that with this implementation, on 64KB system page size kernel, there are 16 uars per system page but only one uars is used. The other 15 uars are ignored because of the above assumption. Regarding SR-IOV, mlx4_core in hypervisor will set the uar page size to 4KB and mlx4_core code in virtual OS will obtain the uar page size from firmware. Regarding backward compatibility in SR-IOV, if hypervisor has this new code, the virtual OS must be updated. If hypervisor has old code, and the virtual OS has this new code, the new code will be backward compatible with the old code. If the uar size is big enough, this new code in VF continues to work with 64 KB uar page size (on PowerPc kernel). If the uar size does not meet 128 uars requirement, this new code not loaded in VF and print the same error message as the old code in Hypervisor. Signed-off-by: Huy Nguyen Reviewed-by: Yishai Hadas Signed-off-by: David S. Miller --- drivers/infiniband/hw/mlx4/qp.c | 7 ++- drivers/net/ethernet/mellanox/mlx4/cq.c | 4 +- .../net/ethernet/mellanox/mlx4/en_resources.c | 3 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 4 +- drivers/net/ethernet/mellanox/mlx4/eq.c | 7 ++- drivers/net/ethernet/mellanox/mlx4/main.c | 56 +++++++++++++++---- drivers/net/ethernet/mellanox/mlx4/pd.c | 12 +++- include/linux/mlx4/device.h | 13 +++++ 8 files changed, 84 insertions(+), 22 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index bc5536f00b6c..fd97534762b8 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -1681,9 +1681,12 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp, } if (qp->ibqp.uobject) - context->usr_page = cpu_to_be32(to_mucontext(ibqp->uobject->context)->uar.index); + context->usr_page = cpu_to_be32( + mlx4_to_hw_uar_index(dev->dev, + to_mucontext(ibqp->uobject->context)->uar.index)); else - context->usr_page = cpu_to_be32(dev->priv_uar.index); + context->usr_page = cpu_to_be32( + mlx4_to_hw_uar_index(dev->dev, dev->priv_uar.index)); if (attr_mask & IB_QP_DEST_QPN) context->remote_qpn = cpu_to_be32(attr->dest_qp_num); diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c index 3348e646db70..a849da92f857 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/cq.c @@ -318,7 +318,9 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, if (timestamp_en) cq_context->flags |= cpu_to_be32(1 << 19); - cq_context->logsize_usrpage = cpu_to_be32((ilog2(nent) << 24) | uar->index); + cq_context->logsize_usrpage = + cpu_to_be32((ilog2(nent) << 24) | + mlx4_to_hw_uar_index(dev, uar->index)); cq_context->comp_eqn = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn; cq_context->log_page_size = mtt->page_shift - MLX4_ICM_PAGE_SHIFT; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c index 12aab5a659d3..02e925d6f734 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c @@ -58,7 +58,8 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride, } else { context->sq_size_stride = ilog2(TXBB_SIZE) - 4; } - context->usr_page = cpu_to_be32(mdev->priv_uar.index); + context->usr_page = cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev, + mdev->priv_uar.index)); context->local_qpn = cpu_to_be32(qpn); context->pri_path.ackto = 1 & 0x07; context->pri_path.sched_queue = 0x83 | (priv->port - 1) << 6; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 4421bf5463f6..e0946ab22010 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -213,7 +213,9 @@ int mlx4_en_activate_tx_ring(struct mlx4_en_priv *priv, mlx4_en_fill_qp_context(priv, ring->size, ring->stride, 1, 0, ring->qpn, ring->cqn, user_prio, &ring->context); if (ring->bf_alloced) - ring->context.usr_page = cpu_to_be32(ring->bf.uar->index); + ring->context.usr_page = + cpu_to_be32(mlx4_to_hw_uar_index(mdev->dev, + ring->bf.uar->index)); err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, &ring->context, &ring->qp, &ring->qp_state); diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 4696053165f8..f613977455e0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -940,9 +940,10 @@ static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq) if (!priv->eq_table.uar_map[index]) { priv->eq_table.uar_map[index] = - ioremap(pci_resource_start(dev->persist->pdev, 2) + - ((eq->eqn / 4) << PAGE_SHIFT), - PAGE_SIZE); + ioremap( + pci_resource_start(dev->persist->pdev, 2) + + ((eq->eqn / 4) << (dev->uar_page_shift)), + (1 << (dev->uar_page_shift))); if (!priv->eq_table.uar_map[index]) { mlx4_err(dev, "Couldn't map EQ doorbell for EQN 0x%06x\n", eq->eqn); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index f1b6d219e445..2cc3c626c3fe 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -168,6 +168,20 @@ struct mlx4_port_config { static atomic_t pf_loading = ATOMIC_INIT(0); +static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev, + struct mlx4_dev_cap *dev_cap) +{ + /* The reserved_uars is calculated by system page size unit. + * Therefore, adjustment is added when the uar page size is less + * than the system page size + */ + dev->caps.reserved_uars = + max_t(int, + mlx4_get_num_reserved_uar(dev), + dev_cap->reserved_uars / + (1 << (PAGE_SHIFT - dev->uar_page_shift))); +} + int mlx4_check_port_params(struct mlx4_dev *dev, enum mlx4_port_type *port_type) { @@ -386,8 +400,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.reserved_mtts = dev_cap->reserved_mtts; dev->caps.reserved_mrws = dev_cap->reserved_mrws; - /* The first 128 UARs are used for EQ doorbells */ - dev->caps.reserved_uars = max_t(int, 128, dev_cap->reserved_uars); dev->caps.reserved_pds = dev_cap->reserved_pds; dev->caps.reserved_xrcds = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ? dev_cap->reserved_xrcds : 0; @@ -405,6 +417,15 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev->caps.max_gso_sz = dev_cap->max_gso_sz; dev->caps.max_rss_tbl_sz = dev_cap->max_rss_tbl_sz; + /* Save uar page shift */ + if (!mlx4_is_slave(dev)) { + /* Virtual PCI function needs to determine UAR page size from + * firmware. Only master PCI function can set the uar page size + */ + dev->uar_page_shift = DEFAULT_UAR_PAGE_SHIFT; + mlx4_set_num_reserved_uars(dev, dev_cap); + } + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_PHV_EN) { struct mlx4_init_hca_param hca_param; @@ -815,16 +836,25 @@ static int mlx4_slave_cap(struct mlx4_dev *dev) return -ENODEV; } - /* slave gets uar page size from QUERY_HCA fw command */ - dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12); + /* Set uar_page_shift for VF */ + dev->uar_page_shift = hca_param.uar_page_sz + 12; - /* TODO: relax this assumption */ - if (dev->caps.uar_page_size != PAGE_SIZE) { - mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n", - dev->caps.uar_page_size, PAGE_SIZE); - return -ENODEV; + /* Make sure the master uar page size is valid */ + if (dev->uar_page_shift > PAGE_SHIFT) { + mlx4_err(dev, + "Invalid configuration: uar page size is larger than system page size\n"); + return -ENODEV; } + /* Set reserved_uars based on the uar_page_shift */ + mlx4_set_num_reserved_uars(dev, &dev_cap); + + /* Although uar page size in FW differs from system page size, + * upper software layers (mlx4_ib, mlx4_en and part of mlx4_core) + * still works with assumption that uar page size == system page size + */ + dev->caps.uar_page_size = PAGE_SIZE; + memset(&func_cap, 0, sizeof(func_cap)); err = mlx4_QUERY_FUNC_CAP(dev, 0, &func_cap); if (err) { @@ -2179,8 +2209,12 @@ static int mlx4_init_hca(struct mlx4_dev *dev) dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; - init_hca.log_uar_sz = ilog2(dev->caps.num_uars); - init_hca.uar_page_sz = PAGE_SHIFT - 12; + /* Always set UAR page size 4KB, set log_uar_sz accordingly */ + init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + + PAGE_SHIFT - + DEFAULT_UAR_PAGE_SHIFT; + init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + init_hca.mw_enabled = 0; if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c index 609c59dc854e..b3cc3ab63799 100644 --- a/drivers/net/ethernet/mellanox/mlx4/pd.c +++ b/drivers/net/ethernet/mellanox/mlx4/pd.c @@ -269,9 +269,15 @@ EXPORT_SYMBOL_GPL(mlx4_bf_free); int mlx4_init_uar_table(struct mlx4_dev *dev) { - if (dev->caps.num_uars <= 128) { - mlx4_err(dev, "Only %d UAR pages (need more than 128)\n", - dev->caps.num_uars); + int num_reserved_uar = mlx4_get_num_reserved_uar(dev); + + mlx4_dbg(dev, "uar_page_shift = %d", dev->uar_page_shift); + mlx4_dbg(dev, "Effective reserved_uars=%d", dev->caps.reserved_uars); + + if (dev->caps.num_uars <= num_reserved_uar) { + mlx4_err( + dev, "Only %d UAR pages (need more than %d)\n", + dev->caps.num_uars, num_reserved_uar); mlx4_err(dev, "Increase firmware log2_uar_bar_megabytes?\n"); return -ENODEV; } diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 430a929f048b..a0e8cc8dcc67 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -44,6 +44,8 @@ #include +#define DEFAULT_UAR_PAGE_SHIFT 12 + #define MAX_MSIX_P_PORT 17 #define MAX_MSIX 64 #define MIN_MSIX_P_PORT 5 @@ -856,6 +858,7 @@ struct mlx4_dev { u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; struct mlx4_vf_dev *dev_vfs; + u8 uar_page_shift; }; struct mlx4_clock_params { @@ -1528,4 +1531,14 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev, int mlx4_get_internal_clock_params(struct mlx4_dev *dev, struct mlx4_clock_params *params); +static inline int mlx4_to_hw_uar_index(struct mlx4_dev *dev, int index) +{ + return (index << (PAGE_SHIFT - dev->uar_page_shift)); +} + +static inline int mlx4_get_num_reserved_uar(struct mlx4_dev *dev) +{ + /* The first 128 UARs are used for EQ doorbells */ + return (128 >> (PAGE_SHIFT - dev->uar_page_shift)); +} #endif /* MLX4_DEVICE_H */ From 925ab1aa9394bbaeac47ee5b65d3fdf0fb8135cf Mon Sep 17 00:00:00 2001 From: Eugenia Emantayev Date: Wed, 17 Feb 2016 17:24:27 +0200 Subject: [PATCH 261/489] net/mlx4_en: Avoid changing dev->features directly in run-time It's forbidden to manually change dev->features in run-time. Currently, this is done in the driver to make sure that GSO_UDP_TUNNEL is advertized only when VXLAN tunnel is set. However, since the stack actually does features intersection with hw_enc_features, we can safely revert to advertizing features early when registering the netdevice. Fixes: f4a1edd56120 ('net/mlx4_en: Advertize encapsulation offloads [...]') Signed-off-by: Eugenia Emantayev Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 0c7e3f69a73b..f191a1612589 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2344,8 +2344,6 @@ out: /* set offloads */ priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL; - priv->dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features |= NETIF_F_GSO_UDP_TUNNEL; } static void mlx4_en_del_vxlan_offloads(struct work_struct *work) @@ -2356,8 +2354,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work) /* unset offloads */ priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM | NETIF_F_TSO | NETIF_F_GSO_UDP_TUNNEL); - priv->dev->hw_features &= ~NETIF_F_GSO_UDP_TUNNEL; - priv->dev->features &= ~NETIF_F_GSO_UDP_TUNNEL; ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 0); @@ -2980,6 +2976,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } + if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL; + } + mdev->pndev[port] = dev; mdev->upper[port] = NULL; From cd772de358d6e001d308292c542f7908511287a4 Mon Sep 17 00:00:00 2001 From: "Woojung.Huh@microchip.com" Date: Thu, 11 Feb 2016 17:29:47 +0000 Subject: [PATCH 262/489] phy: keep pause flags in phy driver features genphy_config_init() masked out pause flags set in phy driver structure. Pause flags needs to be preserved in phydev->supported & phydev->advertising. Signed-off-by: Woojung Huh Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index bad3f005faee..e551f3a89cfd 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -1410,7 +1410,7 @@ int genphy_config_init(struct phy_device *phydev) features = (SUPPORTED_TP | SUPPORTED_MII | SUPPORTED_AUI | SUPPORTED_FIBRE | - SUPPORTED_BNC); + SUPPORTED_BNC | SUPPORTED_Pause | SUPPORTED_Asym_Pause); /* Do we support autonegotiation? */ val = phy_read(phydev, MII_BMSR); From d148bbd37a52b030b131ac5408c0f8293325ca0b Mon Sep 17 00:00:00 2001 From: David Rivshin Date: Fri, 12 Feb 2016 19:45:36 -0500 Subject: [PATCH 263/489] drivers: net: cpsw-phy-sel: add dev_warn() for unsupported PHY mode The cpsw-phy-sel driver supports only MII, RMII, and RGMII PHY modes, and silently handled any other values as if MII was specified. In a case where the PHY mode was incorrectly specified, or a bug elsewhere, there would be no indication of a problem. If MII was the correct mode, then this will go unnoticed, otherwise the symptom will be a failure to transmit/receive data over the RMII/RGMII link. Add a dev_warn() to make this condition obvious and provide a breadcrumb to follow. Cc: Mugunthan V N Signed-off-by: David Rivshin Acked-by: Mugunthan V N Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/cpsw-phy-sel.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/ti/cpsw-phy-sel.c b/drivers/net/ethernet/ti/cpsw-phy-sel.c index e9cc61e1ec74..c3e85acfdc70 100644 --- a/drivers/net/ethernet/ti/cpsw-phy-sel.c +++ b/drivers/net/ethernet/ti/cpsw-phy-sel.c @@ -63,8 +63,12 @@ static void cpsw_gmii_sel_am3352(struct cpsw_phy_sel_priv *priv, mode = AM33XX_GMII_SEL_MODE_RGMII; break; - case PHY_INTERFACE_MODE_MII: default: + dev_warn(priv->dev, + "Unsupported PHY mode: \"%s\". Defaulting to MII.\n", + phy_modes(phy_mode)); + /* fallthrough */ + case PHY_INTERFACE_MODE_MII: mode = AM33XX_GMII_SEL_MODE_MII; break; }; @@ -106,8 +110,12 @@ static void cpsw_gmii_sel_dra7xx(struct cpsw_phy_sel_priv *priv, mode = AM33XX_GMII_SEL_MODE_RGMII; break; - case PHY_INTERFACE_MODE_MII: default: + dev_warn(priv->dev, + "Unsupported PHY mode: \"%s\". Defaulting to MII.\n", + phy_modes(phy_mode)); + /* fallthrough */ + case PHY_INTERFACE_MODE_MII: mode = AM33XX_GMII_SEL_MODE_MII; break; }; From d9dfd8d741683347ee159d25f5b50c346a0df557 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Wed, 17 Feb 2016 10:41:41 -0500 Subject: [PATCH 264/489] NFSv4: Fix a dentry leak on alias use In the case where d_add_unique() finds an appropriate alias to use it will have already incremented the reference count. An additional dget() to swap the open context's dentry is unnecessary and will leak a reference. Signed-off-by: Benjamin Coddington Fixes: 275bb307865a3 ("NFSv4: Move dentry instantiation into the NFSv4-...") Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Trond Myklebust --- fs/nfs/nfs4proc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 4bfc33ad0563..14881594dd07 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -2466,9 +2466,9 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, dentry = d_add_unique(dentry, igrab(state->inode)); if (dentry == NULL) { dentry = opendata->dentry; - } else if (dentry != ctx->dentry) { + } else { dput(ctx->dentry); - ctx->dentry = dget(dentry); + ctx->dentry = dentry; } nfs_set_verifier(dentry, nfs_save_change_attribute(d_inode(opendata->dir))); From 4bdf87ebda016b864b388f96ae349e76983ebac4 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 17 Feb 2016 15:48:28 +0100 Subject: [PATCH 265/489] nfs4: fix stateid handling for the NFS v4.2 operations The newly added NFS v4.2 operations (ALLOCATE, DEALLOCATE, SEEK and CLONE) use a helper called nfs42_set_rw_stateid to select a stateid that is sent to the server. But they don't set the inode and state fields in the nfs4_exception structure, and this don't partake in the stateid recovery protocol. Because of this they will simply return errors insted of trying to recover a stateid when the server return a BAD_STATEID error. Additionally CLONE has the problem that it operates on two files and thus two stateids, and thus needs to call the exception handler twice to recover stateids. While we're at it stop grabbing an addititional reference to the open context in all these operations - having the file open guarantees that the open context won't go away. All this can be produces with the generic/168 and generic/170 tests in xfstests which stress the CLONE stateid handling. Signed-off-by: Christoph Hellwig Signed-off-by: Trond Myklebust --- fs/nfs/nfs42proc.c | 119 +++++++++++++++++++++++++++++---------------- 1 file changed, 76 insertions(+), 43 deletions(-) diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index bd25dc7077f7..dff83460e5a6 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -16,29 +16,8 @@ #define NFSDBG_FACILITY NFSDBG_PROC -static int nfs42_set_rw_stateid(nfs4_stateid *dst, struct file *file, - fmode_t fmode) -{ - struct nfs_open_context *open; - struct nfs_lock_context *lock; - int ret; - - open = get_nfs_open_context(nfs_file_open_context(file)); - lock = nfs_get_lock_context(open); - if (IS_ERR(lock)) { - put_nfs_open_context(open); - return PTR_ERR(lock); - } - - ret = nfs4_set_rw_stateid(dst, open, lock, fmode); - - nfs_put_lock_context(lock); - put_nfs_open_context(open); - return ret; -} - static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, - loff_t offset, loff_t len) + struct nfs_lock_context *lock, loff_t offset, loff_t len) { struct inode *inode = file_inode(filep); struct nfs_server *server = NFS_SERVER(inode); @@ -56,7 +35,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.falloc_stateid, filep, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.falloc_stateid, lock->open_context, + lock, FMODE_WRITE); if (status) return status; @@ -78,15 +58,26 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; int err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_fallocate(msg, filep, offset, len); - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + err = _nfs42_proc_fallocate(msg, filep, lock, offset, len); + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -135,7 +126,8 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) return err; } -static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) +static loff_t _nfs42_proc_llseek(struct file *filep, + struct nfs_lock_context *lock, loff_t offset, int whence) { struct inode *inode = file_inode(filep); struct nfs42_seek_args args = { @@ -156,7 +148,8 @@ static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) if (!nfs_server_capable(inode, NFS_CAP_SEEK)) return -ENOTSUPP; - status = nfs42_set_rw_stateid(&args.sa_stateid, filep, FMODE_READ); + status = nfs4_set_rw_stateid(&args.sa_stateid, lock->open_context, + lock, FMODE_READ); if (status) return status; @@ -175,17 +168,28 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence) { struct nfs_server *server = NFS_SERVER(file_inode(filep)); struct nfs4_exception exception = { }; + struct nfs_lock_context *lock; loff_t err; + lock = nfs_get_lock_context(nfs_file_open_context(filep)); + if (IS_ERR(lock)) + return PTR_ERR(lock); + + exception.inode = file_inode(filep); + exception.state = lock->open_context->state; + do { - err = _nfs42_proc_llseek(filep, offset, whence); + err = _nfs42_proc_llseek(filep, lock, offset, whence); if (err >= 0) break; - if (err == -ENOTSUPP) - return -EOPNOTSUPP; + if (err == -ENOTSUPP) { + err = -EOPNOTSUPP; + break; + } err = nfs4_handle_exception(server, err, &exception); } while (exception.retry); + nfs_put_lock_context(lock); return err; } @@ -298,8 +302,9 @@ int nfs42_proc_layoutstats_generic(struct nfs_server *server, } static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, - struct file *dst_f, loff_t src_offset, - loff_t dst_offset, loff_t count) + struct file *dst_f, struct nfs_lock_context *src_lock, + struct nfs_lock_context *dst_lock, loff_t src_offset, + loff_t dst_offset, loff_t count) { struct inode *src_inode = file_inode(src_f); struct inode *dst_inode = file_inode(dst_f); @@ -320,11 +325,13 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, msg->rpc_argp = &args; msg->rpc_resp = &res; - status = nfs42_set_rw_stateid(&args.src_stateid, src_f, FMODE_READ); + status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context, + src_lock, FMODE_READ); if (status) return status; - status = nfs42_set_rw_stateid(&args.dst_stateid, dst_f, FMODE_WRITE); + status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context, + dst_lock, FMODE_WRITE); if (status) return status; @@ -349,22 +356,48 @@ int nfs42_proc_clone(struct file *src_f, struct file *dst_f, }; struct inode *inode = file_inode(src_f); struct nfs_server *server = NFS_SERVER(file_inode(src_f)); - struct nfs4_exception exception = { }; - int err; + struct nfs_lock_context *src_lock; + struct nfs_lock_context *dst_lock; + struct nfs4_exception src_exception = { }; + struct nfs4_exception dst_exception = { }; + int err, err2; if (!nfs_server_capable(inode, NFS_CAP_CLONE)) return -EOPNOTSUPP; + src_lock = nfs_get_lock_context(nfs_file_open_context(src_f)); + if (IS_ERR(src_lock)) + return PTR_ERR(src_lock); + + src_exception.inode = file_inode(src_f); + src_exception.state = src_lock->open_context->state; + + dst_lock = nfs_get_lock_context(nfs_file_open_context(dst_f)); + if (IS_ERR(dst_lock)) { + err = PTR_ERR(dst_lock); + goto out_put_src_lock; + } + + dst_exception.inode = file_inode(dst_f); + dst_exception.state = dst_lock->open_context->state; + do { - err = _nfs42_proc_clone(&msg, src_f, dst_f, src_offset, - dst_offset, count); + err = _nfs42_proc_clone(&msg, src_f, dst_f, src_lock, dst_lock, + src_offset, dst_offset, count); if (err == -ENOTSUPP || err == -EOPNOTSUPP) { NFS_SERVER(inode)->caps &= ~NFS_CAP_CLONE; - return -EOPNOTSUPP; + err = -EOPNOTSUPP; + break; } - err = nfs4_handle_exception(server, err, &exception); - } while (exception.retry); + err2 = nfs4_handle_exception(server, err, &src_exception); + err = nfs4_handle_exception(server, err, &dst_exception); + if (!err) + err = err2; + } while (src_exception.retry || dst_exception.retry); + + nfs_put_lock_context(dst_lock); +out_put_src_lock: + nfs_put_lock_context(src_lock); return err; - } From c89757061a4e4017a21ef632dc100449a7bab7dd Mon Sep 17 00:00:00 2001 From: Kinglong Mee Date: Mon, 1 Feb 2016 09:39:29 +0800 Subject: [PATCH 266/489] pnfs/blocklayout: fix a memeory leak when using,vmalloc_to_page unreferenced object 0xffffc90000abf000 (size 16900): comm "fsync02", pid 15765, jiffies 4297431627 (age 423.772s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 a0 c2 19 00 88 ff ff ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [] kmemleak_alloc+0x4e/0xb0 [] __vmalloc_node_range+0x231/0x280 [] __vmalloc+0x4a/0x50 [] ext_tree_prepare_commit+0x231/0x2e0 [blocklayoutdriver] [] bl_prepare_layoutcommit+0xe/0x10 [blocklayoutdriver] [] pnfs_layoutcommit_inode+0x29c/0x330 [nfsv4] [] pnfs_generic_sync+0x13/0x20 [nfsv4] [] nfs4_file_fsync+0x58/0x150 [nfsv4] [] vfs_fsync_range+0x4b/0xb0 [] do_fsync+0x3d/0x70 [] SyS_fsync+0x10/0x20 [] entry_SYSCALL_64_fastpath+0x12/0x76 [] 0xffffffffffffffff v2, add missing include header Signed-off-by: Kinglong Mee Signed-off-by: Trond Myklebust --- fs/nfs/blocklayout/extent_tree.c | 10 ++++++++-- include/linux/nfs_xdr.h | 1 + 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/fs/nfs/blocklayout/extent_tree.c b/fs/nfs/blocklayout/extent_tree.c index c59a59c37f3d..35ab51c04814 100644 --- a/fs/nfs/blocklayout/extent_tree.c +++ b/fs/nfs/blocklayout/extent_tree.c @@ -476,6 +476,7 @@ static void ext_tree_free_commitdata(struct nfs4_layoutcommit_args *arg, for (i = 0; i < nr_pages; i++) put_page(arg->layoutupdate_pages[i]); + vfree(arg->start_p); kfree(arg->layoutupdate_pages); } else { put_page(arg->layoutupdate_page); @@ -559,10 +560,15 @@ retry: if (unlikely(arg->layoutupdate_pages != &arg->layoutupdate_page)) { void *p = start_p, *end = p + arg->layoutupdate_len; + struct page *page = NULL; int i = 0; - for ( ; p < end; p += PAGE_SIZE) - arg->layoutupdate_pages[i++] = vmalloc_to_page(p); + arg->start_p = start_p; + for ( ; p < end; p += PAGE_SIZE) { + page = vmalloc_to_page(p); + arg->layoutupdate_pages[i++] = page; + get_page(page); + } } dprintk("%s found %zu ranges\n", __func__, count); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 791098a08a87..d320906cf13e 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -275,6 +275,7 @@ struct nfs4_layoutcommit_args { size_t layoutupdate_len; struct page *layoutupdate_page; struct page **layoutupdate_pages; + __be32 *start_p; }; struct nfs4_layoutcommit_res { From 437b300c6b28040ad87e4caf042e05f2c5f13c6d Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Tue, 16 Feb 2016 16:20:25 -0500 Subject: [PATCH 267/489] auth_gss: fix panic in gss_pipe_downcall() in fips mode On Mon, 15 Feb 2016, Trond Myklebust wrote: > Hi Scott, > > On Mon, Feb 15, 2016 at 2:28 PM, Scott Mayhew wrote: > > md5 is disabled in fips mode, and attempting to import a gss context > > using md5 while in fips mode will result in crypto_alg_mod_lookup() > > returning -ENOENT, which will make its way back up to > > gss_pipe_downcall(), where the BUG() is triggered. Handling the -ENOENT > > allows for a more graceful failure. > > > > Signed-off-by: Scott Mayhew > > --- > > net/sunrpc/auth_gss/auth_gss.c | 3 +++ > > 1 file changed, 3 insertions(+) > > > > diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c > > index 799e65b..c30fc3b 100644 > > --- a/net/sunrpc/auth_gss/auth_gss.c > > +++ b/net/sunrpc/auth_gss/auth_gss.c > > @@ -737,6 +737,9 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) > > case -ENOSYS: > > gss_msg->msg.errno = -EAGAIN; > > break; > > + case -ENOENT: > > + gss_msg->msg.errno = -EPROTONOSUPPORT; > > + break; > > default: > > printk(KERN_CRIT "%s: bad return from " > > "gss_fill_context: %zd\n", __func__, err); > > -- > > 2.4.3 > > > > Well debugged, but I unfortunately do have to ask if this patch is > sufficient? In addition to -ENOENT, and -ENOMEM, it looks to me as if > crypto_alg_mod_lookup() can also fail with -EINTR, -ETIMEDOUT, and > -EAGAIN. Don't we also want to handle those? You're right, I was focusing on the panic that I could easily reproduce. I'm still not sure how I could trigger those other conditions. > > In fact, peering into the rats nest that is > gss_import_sec_context_kerberos(), it looks as if that is just a tiny > subset of all the errors that we might run into. Perhaps the right > thing to do here is to get rid of the BUG() (but keep the above > printk) and just return a generic error? That sounds fine to me -- updated patch attached. -Scott >From d54c6b64a107a90a38cab97577de05f9a4625052 Mon Sep 17 00:00:00 2001 From: Scott Mayhew Date: Mon, 15 Feb 2016 15:12:19 -0500 Subject: [PATCH] auth_gss: remove the BUG() from gss_pipe_downcall() Instead return a generic error via gss_msg->msg.errno. None of the errors returned by gss_fill_context() should necessarily trigger a kernel panic. Signed-off-by: Scott Mayhew Signed-off-by: Trond Myklebust --- net/sunrpc/auth_gss/auth_gss.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 799e65b944b9..cabf586f47d7 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -740,7 +740,7 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) default: printk(KERN_CRIT "%s: bad return from " "gss_fill_context: %zd\n", __func__, err); - BUG(); + gss_msg->msg.errno = -EIO; } goto err_release_msg; } From 18f922d037211a15543af935861bf92161e697e9 Mon Sep 17 00:00:00 2001 From: Alan Date: Wed, 17 Feb 2016 14:15:30 +0000 Subject: [PATCH 268/489] blk: fix overflow in queue_discard_max_hw_show We get this right for queue_discard_max_show but not max_hw_show. Follow the same pattern as queue_discard_max_show instead so that we don't truncate. Signed-off-by: Alan Cox Signed-off-by: Jens Axboe --- block/blk-sysfs.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index e140cc487ce1..dd93763057ce 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -147,10 +147,9 @@ static ssize_t queue_discard_granularity_show(struct request_queue *q, char *pag static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page) { - unsigned long long val; - val = q->limits.max_hw_discard_sectors << 9; - return sprintf(page, "%llu\n", val); + return sprintf(page, "%llu\n", + (unsigned long long)q->limits.max_hw_discard_sectors << 9); } static ssize_t queue_discard_max_show(struct request_queue *q, char *page) From 2eca0d6ceea1f108b2d3ac81fb34698c4fd41006 Mon Sep 17 00:00:00 2001 From: Shanker Donthineni Date: Tue, 16 Feb 2016 18:00:36 -0600 Subject: [PATCH 269/489] irqchip/gicv3-its: Avoid cache flush beyond ITS_BASERn memory size Function its_alloc_tables() maintains two local variables, "order" and and "alloc_size", to hold memory size that has been allocated to ITS_BASEn. We don't always refresh the variable alloc_size whenever value of the variable order changes, causing the following two problems. - Cache flush operation with size more than required. - Information reported by pr_info is not correct. Use a helper macro that converts page order to size in bytes instead of variable "alloc_size" to fix both the problems. Signed-off-by: Shanker Donthineni Signed-off-by: Marc Zyngier --- drivers/irqchip/irq-gic-v3-its.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index ff2be77a51f6..43dfd15c1dd2 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -78,6 +78,9 @@ struct its_node { #define ITS_ITT_ALIGN SZ_256 +/* Convert page order to size in bytes */ +#define PAGE_ORDER_TO_SIZE(o) (PAGE_SIZE << (o)) + struct event_lpi_map { unsigned long *lpi_map; u16 *col_map; @@ -841,7 +844,6 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) u64 type = GITS_BASER_TYPE(val); u64 entry_size = GITS_BASER_ENTRY_SIZE(val); int order = get_order(psz); - int alloc_size; int alloc_pages; u64 tmp; void *base; @@ -873,9 +875,8 @@ static int its_alloc_tables(const char *node_name, struct its_node *its) } } - alloc_size = (1 << order) * PAGE_SIZE; retry_alloc_baser: - alloc_pages = (alloc_size / psz); + alloc_pages = (PAGE_ORDER_TO_SIZE(order) / psz); if (alloc_pages > GITS_BASER_PAGES_MAX) { alloc_pages = GITS_BASER_PAGES_MAX; order = get_order(GITS_BASER_PAGES_MAX * psz); @@ -928,7 +929,7 @@ retry_baser: shr = tmp & GITS_BASER_SHAREABILITY_MASK; if (!shr) { cache = GITS_BASER_nC; - __flush_dcache_area(base, alloc_size); + __flush_dcache_area(base, PAGE_ORDER_TO_SIZE(order)); } goto retry_baser; } @@ -961,7 +962,7 @@ retry_baser: } pr_info("ITS: allocated %d %s @%lx (psz %dK, shr %d)\n", - (int)(alloc_size / entry_size), + (int)(PAGE_ORDER_TO_SIZE(order) / entry_size), its_base_type_string[type], (unsigned long)virt_to_phys(base), psz / SZ_1K, (int)shr >> GITS_BASER_SHAREABILITY_SHIFT); From fe25d078874f2c29c38f4160467d74f5756537c9 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Feb 2016 12:26:33 -0600 Subject: [PATCH 270/489] Revert "x86/PCI: Don't alloc pcibios-irq when MSI is enabled" Revert 8affb487d4a4 ("x86/PCI: Don't alloc pcibios-irq when MSI is enabled"). This is part of reverting 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") to fix regressions it introduced. Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211 Fixes: 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki CC: Jiang Liu CC: Joerg Roedel --- arch/x86/pci/common.c | 8 -------- 1 file changed, 8 deletions(-) diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index 2879efc73a96..cb499c5b6ae5 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -713,14 +713,6 @@ int pcibios_add_device(struct pci_dev *dev) int pcibios_alloc_irq(struct pci_dev *dev) { - /* - * If the PCI device was already claimed by core code and has - * MSI enabled, probing of the pcibios IRQ will overwrite - * dev->irq. So bail out if MSI is already enabled. - */ - if (pci_dev_msi_enabled(dev)) - return -EBUSY; - return pcibios_enable_irq(dev); } From 853effc55b0f975abd6d318cca486a9c1b67e10f Mon Sep 17 00:00:00 2001 From: Mark Tomlinson Date: Mon, 15 Feb 2016 16:24:44 +1300 Subject: [PATCH 271/489] l2tp: Fix error creating L2TP tunnels A previous commit (33f72e6) added notification via netlink for tunnels when created/modified/deleted. If the notification returned an error, this error was returned from the tunnel function. If there were no listeners, the error code ESRCH was returned, even though having no listeners is not an error. Other calls to this and other similar notification functions either ignore the error code, or filter ESRCH. This patch checks for ESRCH and does not flag this as an error. Reviewed-by: Hamish Martin Signed-off-by: Mark Tomlinson Signed-off-by: David S. Miller --- net/l2tp/l2tp_netlink.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f93c5be612a7..2caaa84ce92d 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -124,8 +124,13 @@ static int l2tp_tunnel_notify(struct genl_family *family, ret = l2tp_nl_tunnel_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, tunnel, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); @@ -147,8 +152,13 @@ static int l2tp_session_notify(struct genl_family *family, ret = l2tp_nl_session_send(msg, info->snd_portid, info->snd_seq, NLM_F_ACK, session, cmd); - if (ret >= 0) - return genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + if (ret >= 0) { + ret = genlmsg_multicast_allns(family, msg, 0, 0, GFP_ATOMIC); + /* We don't care if no one is listening */ + if (ret == -ESRCH) + ret = 0; + return ret; + } nlmsg_free(msg); From 1e5ad30c649a82a062ce79a87c1296e6c6f328c2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 15 Feb 2016 13:19:53 +0100 Subject: [PATCH 272/489] mlxsw: Treat local port 64 as valid MLXSW_PORT_MAX_PORTS represents the maximum number of local ports, which is 65 for both ASICs (SwitchX-2 and Spectrum) supported by this driver. Fixes: 93c1edb27f9e ("mlxsw: Introduce Mellanox switch driver core") Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/port.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h index 726f5435b32f..ae65b9940aed 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/port.h +++ b/drivers/net/ethernet/mellanox/mlxsw/port.h @@ -49,7 +49,7 @@ #define MLXSW_PORT_MID 0xd000 #define MLXSW_PORT_MAX_PHY_PORTS 0x40 -#define MLXSW_PORT_MAX_PORTS MLXSW_PORT_MAX_PHY_PORTS +#define MLXSW_PORT_MAX_PORTS (MLXSW_PORT_MAX_PHY_PORTS + 1) #define MLXSW_PORT_DEVID_BITS_OFFSET 10 #define MLXSW_PORT_PHY_BITS_OFFSET 4 From 6a9863a62206dad8ad236bcde489978aedb072fa Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Mon, 15 Feb 2016 13:19:54 +0100 Subject: [PATCH 273/489] mlxsw: spectrum: Set STP state when leaving 802.1D bridge When a VLAN device leaves a bridge its STP state is set to DISABLED, which causes the hardware to discard any packets coming through the port with this VLAN. Fix that by setting STP state to FORWARDING when the device leaves its bridge and allow traffic to be directed to CPU. Fixes: 26f0e7fb15de ("mlxsw: spectrum: Add support for VLAN devices bridging") Reported-by: Elad Raz Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 217856bdd400..0fa8da584845 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2746,6 +2746,13 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, goto err_vport_flood_set; } + err = mlxsw_sp_port_stp_state_set(mlxsw_sp_vport, vid, + MLXSW_REG_SPMS_STATE_FORWARDING); + if (err) { + netdev_err(dev, "Failed to set STP state\n"); + goto err_port_stp_state_set; + } + if (flush_fdb && mlxsw_sp_vport_fdb_flush(mlxsw_sp_vport)) netdev_err(dev, "Failed to flush FDB\n"); @@ -2763,6 +2770,7 @@ static int mlxsw_sp_vport_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_vport, return 0; +err_port_stp_state_set: err_vport_flood_set: err_port_vid_learning_set: err_port_vid_to_fid_validate: From 705bcdda81eda8b4b4c564c4be7b8cfad6a180d6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Mon, 15 Feb 2016 13:41:31 +0100 Subject: [PATCH 274/489] ravb: Update DT binding example for final CPG/MSSR bindings The example in the DT binding documentation uses the preliminary DT bindings for the r8a7795 MSTP clocks, which never went upstream. Update the example to use the DT bindings for the upstream Clock Pulse Generator / Module Standby and Software Reset hardware block. Signed-off-by: Geert Uytterhoeven Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/renesas,ravb.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index 81a9f9e6b45f..c8ac222eac67 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -82,8 +82,8 @@ Example: "ch16", "ch17", "ch18", "ch19", "ch20", "ch21", "ch22", "ch23", "ch24"; - clocks = <&mstp8_clks R8A7795_CLK_ETHERAVB>; - power-domains = <&cpg_clocks>; + clocks = <&cpg CPG_MOD 812>; + power-domains = <&cpg>; phy-mode = "rgmii-id"; phy-handle = <&phy0>; From 29e73269aa4d36f92b35610c25f8b01c789b0dc8 Mon Sep 17 00:00:00 2001 From: Guillaume Nault Date: Mon, 15 Feb 2016 17:01:10 +0100 Subject: [PATCH 275/489] pppoe: fix reference counting in PPPoE proxy Drop reference on the relay_po socket when __pppoe_xmit() succeeds. This is already handled correctly in the error path. Signed-off-by: Guillaume Nault Signed-off-by: David S. Miller --- drivers/net/ppp/pppoe.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index f3c63022eb3c..4ddae8118c85 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -395,6 +395,8 @@ static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb) if (!__pppoe_xmit(sk_pppox(relay_po), skb)) goto abort_put; + + sock_put(sk_pppox(relay_po)); } else { if (sock_queue_rcv_skb(sk, skb)) goto abort_kfree; From 7dcd182bec271ab341b05b66b6006995795fc0e7 Mon Sep 17 00:00:00 2001 From: Jessica Yu Date: Tue, 16 Feb 2016 17:32:33 -0500 Subject: [PATCH 276/489] ftrace/module: remove ftrace module notifier Remove the ftrace module notifier in favor of directly calling ftrace_module_enable() and ftrace_release_mod() in the module loader. Hard-coding the function calls directly in the module loader removes dependence on the module notifier call chain and provides better visibility and control over what gets called when, which is important to kernel utilities such as livepatch. This fixes a notifier ordering issue in which the ftrace module notifier (and hence ftrace_module_enable()) for coming modules was being called after klp_module_notify(), which caused livepatch modules to initialize incorrectly. This patch removes dependence on the module notifier call chain in favor of hard coding the corresponding function calls in the module loader. This ensures that ftrace and livepatch code get called in the correct order on patch module load and unload. Fixes: 5156dca34a3e ("ftrace: Fix the race between ftrace and insmod") Signed-off-by: Jessica Yu Reviewed-by: Steven Rostedt Reviewed-by: Petr Mladek Acked-by: Rusty Russell Reviewed-by: Josh Poimboeuf Reviewed-by: Miroslav Benes Signed-off-by: Jiri Kosina --- include/linux/ftrace.h | 6 ++++-- kernel/module.c | 4 ++++ kernel/trace/ftrace.c | 36 +----------------------------------- 3 files changed, 9 insertions(+), 37 deletions(-) diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 0639dcc98195..76dc15e171eb 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -604,6 +604,7 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size); extern int skip_trace(unsigned long ip); extern void ftrace_module_init(struct module *mod); +extern void ftrace_module_enable(struct module *mod); extern void ftrace_release_mod(struct module *mod); extern void ftrace_disable_daemon(void); @@ -613,8 +614,9 @@ static inline int skip_trace(unsigned long ip) { return 0; } static inline int ftrace_force_update(void) { return 0; } static inline void ftrace_disable_daemon(void) { } static inline void ftrace_enable_daemon(void) { } -static inline void ftrace_release_mod(struct module *mod) {} -static inline void ftrace_module_init(struct module *mod) {} +static inline void ftrace_module_init(struct module *mod) { } +static inline void ftrace_module_enable(struct module *mod) { } +static inline void ftrace_release_mod(struct module *mod) { } static inline __init int register_ftrace_command(struct ftrace_func_command *cmd) { return -EINVAL; diff --git a/kernel/module.c b/kernel/module.c index 8358f4697c0c..b05d466cfa02 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -981,6 +981,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + ftrace_release_mod(mod); + async_synchronize_full(); /* Store the name of the last unloaded module for diagnostic purposes */ @@ -3295,6 +3297,7 @@ fail: module_put(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + ftrace_release_mod(mod); free_module(mod); wake_up_all(&module_wq); return ret; @@ -3371,6 +3374,7 @@ static int complete_formation(struct module *mod, struct load_info *info) mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); + ftrace_module_enable(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); return 0; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eca592f977b2..57a6eea84694 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod) mutex_unlock(&ftrace_lock); } -static void ftrace_module_enable(struct module *mod) +void ftrace_module_enable(struct module *mod) { struct dyn_ftrace *rec; struct ftrace_page *pg; @@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod) ftrace_process_locs(mod, mod->ftrace_callsites, mod->ftrace_callsites + mod->num_ftrace_callsites); } - -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - struct module *mod = data; - - switch (val) { - case MODULE_STATE_COMING: - ftrace_module_enable(mod); - break; - case MODULE_STATE_GOING: - ftrace_release_mod(mod); - break; - default: - break; - } - - return 0; -} -#else -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_nb = { - .notifier_call = ftrace_module_notify, - .priority = INT_MIN, /* Run after anything that can remove kprobes */ -}; - void __init ftrace_init(void) { extern unsigned long __start_mcount_loc[]; @@ -5098,10 +5068,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_nb); - if (ret) - pr_warning("Failed to register trace ftrace module exit notifier\n"); - set_ftrace_early_filters(); return; From 79be1a1c9090048f6f327204b8b1cf4ac067b487 Mon Sep 17 00:00:00 2001 From: Clemens Gruber Date: Mon, 15 Feb 2016 23:46:45 +0100 Subject: [PATCH 277/489] phy: marvell: Fix and unify reg-init behavior For the Marvell 88E1510, marvell_of_reg_init was called too late, in the config_aneg function. Since commit 113c74d83eef ("net: phy: turn carrier off on phy attach"), this lead to the link not coming up at boot anymore, due to the phy state machine being stuck at waiting for interrupts (off by default on the 88E1510). For seven other Marvell PHYs, marvell_of_reg_init was not called at all. Add a generic marvell_config_init function, which in turn calls marvell_of_reg_init. PHYs, which already have a specific config_init function with a call to marvell_of_reg_init, are left untouched. The generic marvell_config_init function is called for all the others, to get consistent behavior across all Marvell PHYs. Fixes: 113c74d83eef ("net: phy: turn carrier off on phy attach") Signed-off-by: Clemens Gruber Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/marvell.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index e3eb96443c97..ab1d0fcaf1d9 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -446,6 +446,12 @@ static int m88e1510_config_aneg(struct phy_device *phydev) if (err < 0) return err; + return 0; +} + +static int marvell_config_init(struct phy_device *phydev) +{ + /* Set registers from marvell,reg-init DT property */ return marvell_of_reg_init(phydev); } @@ -495,7 +501,7 @@ static int m88e1116r_config_init(struct phy_device *phydev) mdelay(500); - return 0; + return marvell_config_init(phydev); } static int m88e3016_config_init(struct phy_device *phydev) @@ -514,7 +520,7 @@ static int m88e3016_config_init(struct phy_device *phydev) if (reg < 0) return reg; - return 0; + return marvell_config_init(phydev); } static int m88e1111_config_init(struct phy_device *phydev) @@ -1078,6 +1084,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .probe = marvell_probe, .flags = PHY_HAS_INTERRUPT, + .config_init = &marvell_config_init, .config_aneg = &marvell_config_aneg, .read_status = &genphy_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1149,6 +1156,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, + .config_init = &marvell_config_init, .config_aneg = &m88e1121_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1167,6 +1175,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, + .config_init = &marvell_config_init, .config_aneg = &m88e1318_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1259,6 +1268,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, + .config_init = &marvell_config_init, .config_aneg = &m88e1510_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, @@ -1277,6 +1287,7 @@ static struct phy_driver marvell_drivers[] = { .features = PHY_GBIT_FEATURES, .flags = PHY_HAS_INTERRUPT, .probe = marvell_probe, + .config_init = &marvell_config_init, .config_aneg = &m88e1510_config_aneg, .read_status = &marvell_read_status, .ack_interrupt = &marvell_ack_interrupt, From aeb67ae7d1a318c8456345b8012474be6a3ff74a Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Fri, 29 Jan 2016 10:57:53 +0100 Subject: [PATCH 278/489] irqchip/mxs: Add missing set_handle_irq() The rework of the driver missed to move the call to set_handle_irq() into asm9260_of_init(). As a consequence no interrupt entry point is installed and no interrupts are delivered Solution is: Install the interrupt entry handler. Fixes: 7e4ac676ee ("irqchip/mxs: Add Alphascale ASM9260 support") Signed-off-by: Oleksij Rempel Link: https://lkml.kernel.org/r/1454061473-24957-1-git-send-email-linux@rempel-privat.de Signed-off-by: Jason Cooper --- drivers/irqchip/irq-mxs.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c index c22e2d40cb30..efe50845939d 100644 --- a/drivers/irqchip/irq-mxs.c +++ b/drivers/irqchip/irq-mxs.c @@ -241,6 +241,7 @@ static int __init asm9260_of_init(struct device_node *np, writel(0, icoll_priv.intr + i); icoll_add_domain(np, ASM9260_NUM_IRQS); + set_handle_irq(icoll_handle_irq); return 0; } From 67b4eab91caf2ad574cab1b17ae09180ea2e116e Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Feb 2016 12:26:38 -0600 Subject: [PATCH 279/489] Revert "PCI: Add helpers to manage pci_dev->irq and pci_dev->irq_managed" Revert 811a4e6fce09 ("PCI: Add helpers to manage pci_dev->irq and pci_dev->irq_managed"). This is part of reverting 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") to fix regressions it introduced. Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211 Fixes: 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki CC: Jiang Liu --- arch/x86/pci/intel_mid_pci.c | 4 ++-- arch/x86/pci/irq.c | 10 ++++++---- drivers/acpi/pci_irq.c | 10 ++++++---- include/linux/pci.h | 17 ----------------- 4 files changed, 14 insertions(+), 27 deletions(-) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 0d24e7c10145..8826ff593ebc 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -215,7 +215,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) int polarity; int ret; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; switch (intel_mid_identify_cpu()) { @@ -256,7 +256,7 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (pci_has_managed_irq(dev)) { + if (dev->irq_managed && dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; /* diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 32e70343e6fd..72108f0b66b1 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1202,7 +1202,7 @@ static int pirq_enable_irq(struct pci_dev *dev) struct pci_dev *temp_dev; int irq; - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; irq = IO_APIC_get_PCI_irq_vector(dev->bus->number, @@ -1230,7 +1230,8 @@ static int pirq_enable_irq(struct pci_dev *dev) } dev = temp_dev; if (irq >= 0) { - pci_set_managed_irq(dev, irq); + dev->irq_managed = 1; + dev->irq = irq; dev_info(&dev->dev, "PCI->APIC IRQ transform: " "INT %c -> IRQ %d\n", 'A' + pin - 1, irq); return 0; @@ -1258,8 +1259,9 @@ static int pirq_enable_irq(struct pci_dev *dev) static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && pci_has_managed_irq(dev)) { + if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); - pci_reset_managed_irq(dev); + dev->irq = 0; + dev->irq_managed = 0; } } diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index d30184c7f3bc..9032db7e4b3a 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -406,7 +406,7 @@ int acpi_pci_irq_enable(struct pci_dev *dev) return 0; } - if (pci_has_managed_irq(dev)) + if (dev->irq_managed && dev->irq > 0) return 0; entry = acpi_pci_irq_lookup(dev, pin); @@ -451,7 +451,8 @@ int acpi_pci_irq_enable(struct pci_dev *dev) kfree(entry); return rc; } - pci_set_managed_irq(dev, rc); + dev->irq = rc; + dev->irq_managed = 1; if (link) snprintf(link_desc, sizeof(link_desc), " -> Link[%s]", link); @@ -474,7 +475,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev) u8 pin; pin = dev->pin; - if (!pin || !pci_has_managed_irq(dev)) + if (!pin || !dev->irq_managed || dev->irq <= 0) return; entry = acpi_pci_irq_lookup(dev, pin); @@ -496,6 +497,7 @@ void acpi_pci_irq_disable(struct pci_dev *dev) dev_dbg(&dev->dev, "PCI INT %c disabled\n", pin_name(pin)); if (gsi >= 0) { acpi_unregister_gsi(gsi); - pci_reset_managed_irq(dev); + dev->irq_managed = 0; + dev->irq = 0; } } diff --git a/include/linux/pci.h b/include/linux/pci.h index 27df4a6585da..27716254dcc5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -988,23 +988,6 @@ static inline int pci_is_managed(struct pci_dev *pdev) return pdev->is_managed; } -static inline void pci_set_managed_irq(struct pci_dev *pdev, unsigned int irq) -{ - pdev->irq = irq; - pdev->irq_managed = 1; -} - -static inline void pci_reset_managed_irq(struct pci_dev *pdev) -{ - pdev->irq = 0; - pdev->irq_managed = 0; -} - -static inline bool pci_has_managed_irq(struct pci_dev *pdev) -{ - return pdev->irq_managed && pdev->irq > 0; -} - void pci_disable_device(struct pci_dev *dev); extern unsigned int pcibios_max_latency; From 73dcb556538a4192222c3a919a51e1701bae553b Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Wed, 17 Feb 2016 18:43:22 -0800 Subject: [PATCH 280/489] net: dsa: Unregister slave_dev in error path With commit 0071f56e46da ("dsa: Register netdev before phy"), we are now trying to free a network device that has been previously registered, and in case of errors, this will make us hit the BUG_ON(dev->reg_state != NETREG_UNREGISTERED) condition. Fix this by adding a missing unregister_netdev() before free_netdev(). Fixes: 0071f56e46da ("dsa: Register netdev before phy") Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- net/dsa/slave.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 91e3b2ff364a..ab24521beb4d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1204,6 +1204,7 @@ int dsa_slave_create(struct dsa_switch *ds, struct device *parent, ret = dsa_slave_phy_setup(p, slave_dev); if (ret) { netdev_err(master, "error %d setting up slave phy\n", ret); + unregister_netdev(slave_dev); free_netdev(slave_dev); return ret; } From 1eea84b74cd28773c37bf1bda69915f7b9a67efc Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Mon, 15 Feb 2016 21:30:33 -0500 Subject: [PATCH 281/489] tcp: correctly crypto_alloc_hash return check crypto_alloc_hash never returns NULL Signed-off-by: Insu Yun Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 0c36ef4a3f86..483ffdf5aa4d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2950,7 +2950,7 @@ static void __tcp_alloc_md5sig_pool(void) struct crypto_hash *hash; hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC); - if (IS_ERR_OR_NULL(hash)) + if (IS_ERR(hash)) return; per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash; } From 6a9bab79bb79bd9b2eda16f0aba1b4c43f677be9 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Tue, 16 Feb 2016 16:29:49 +0530 Subject: [PATCH 282/489] net: thunderx: Fix for multiqset not configured upon interface toggle When a interface is assigned morethan 8 queues and the logical interface is toggled i.e down & up, additional queues or qsets are not initialized as secondary qset count is being set to zero while tearing down. Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index c24cb2a86a42..f8012c4847d9 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1125,7 +1125,6 @@ int nicvf_stop(struct net_device *netdev) /* Clear multiqset info */ nic->pnicvf = nic; - nic->sqs_count = 0; return 0; } From 8d210d54c5250c52b69266f299e64fe8356f9453 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Tue, 16 Feb 2016 16:29:50 +0530 Subject: [PATCH 283/489] net: thunderx: Fix for HW TSO not enabled for secondary qsets For secondary Qsets 'hw_tso' is not getting set as probe() returns much earlier. Fixed it by moving silicon revision check. Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index f8012c4847d9..84c5a33f5760 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1537,6 +1537,9 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) nicvf_send_vf_struct(nic); + if (!pass1_silicon(nic->pdev)) + nic->hw_tso = true; + /* Check if this VF is in QS only mode */ if (nic->sqs_mode) return 0; @@ -1556,9 +1559,6 @@ static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; - if (!pass1_silicon(nic->pdev)) - nic->hw_tso = true; - netdev->netdev_ops = &nicvf_netdev_ops; netdev->watchdog_timeo = NICVF_TX_TIMEOUT; From ad2ecebd67d8a80fe5412d11df375a5ed2db7cd1 Mon Sep 17 00:00:00 2001 From: Sunil Goutham Date: Tue, 16 Feb 2016 16:29:51 +0530 Subject: [PATCH 284/489] net: thunderx: Fix receive packet stats Counting rx packets for every CQE_RX in CQ irq handler is incorrect. Synchronization is missing when multiple queues are receiving packets simultaneously. Like transmit packet stats use HW stats here. Also removed unused 'cqe_type' parameter in nicvf_rcv_pkt_handler(). Signed-off-by: Sunil Goutham Signed-off-by: David S. Miller --- drivers/net/ethernet/cavium/thunder/nicvf_main.c | 11 ++++++----- drivers/net/ethernet/cavium/thunder/nicvf_queues.c | 8 ++------ drivers/net/ethernet/cavium/thunder/nicvf_queues.h | 3 +-- 3 files changed, 9 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 84c5a33f5760..a009bc30dc4d 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -574,8 +574,7 @@ static inline void nicvf_set_rxhash(struct net_device *netdev, static void nicvf_rcv_pkt_handler(struct net_device *netdev, struct napi_struct *napi, - struct cmp_queue *cq, - struct cqe_rx_t *cqe_rx, int cqe_type) + struct cqe_rx_t *cqe_rx) { struct sk_buff *skb; struct nicvf *nic = netdev_priv(netdev); @@ -591,7 +590,7 @@ static void nicvf_rcv_pkt_handler(struct net_device *netdev, } /* Check for errors */ - err = nicvf_check_cqe_rx_errs(nic, cq, cqe_rx); + err = nicvf_check_cqe_rx_errs(nic, cqe_rx); if (err && !cqe_rx->rb_cnt) return; @@ -682,8 +681,7 @@ loop: cq_idx, cq_desc->cqe_type); switch (cq_desc->cqe_type) { case CQE_TYPE_RX: - nicvf_rcv_pkt_handler(netdev, napi, cq, - cq_desc, CQE_TYPE_RX); + nicvf_rcv_pkt_handler(netdev, napi, cq_desc); work_done++; break; case CQE_TYPE_SEND: @@ -1353,6 +1351,9 @@ void nicvf_update_stats(struct nicvf *nic) drv_stats->tx_frames_ok = stats->tx_ucast_frames_ok + stats->tx_bcast_frames_ok + stats->tx_mcast_frames_ok; + drv_stats->rx_frames_ok = stats->rx_ucast_frames + + stats->rx_bcast_frames + + stats->rx_mcast_frames; drv_stats->rx_drops = stats->rx_drop_red + stats->rx_drop_overrun; drv_stats->tx_drops = stats->tx_drops; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index d0d1b5490061..767347b1f631 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -1329,16 +1329,12 @@ void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx) } /* Check for errors in the receive cmp.queue entry */ -int nicvf_check_cqe_rx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_rx_t *cqe_rx) +int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx) { struct nicvf_hw_stats *stats = &nic->hw_stats; - struct nicvf_drv_stats *drv_stats = &nic->drv_stats; - if (!cqe_rx->err_level && !cqe_rx->err_opcode) { - drv_stats->rx_frames_ok++; + if (!cqe_rx->err_level && !cqe_rx->err_opcode) return 0; - } if (netif_msg_rx_err(nic)) netdev_err(nic->netdev, diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h index c5030a7f213a..6673e1133523 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h @@ -338,8 +338,7 @@ u64 nicvf_queue_reg_read(struct nicvf *nic, /* Stats */ void nicvf_update_rq_stats(struct nicvf *nic, int rq_idx); void nicvf_update_sq_stats(struct nicvf *nic, int sq_idx); -int nicvf_check_cqe_rx_errs(struct nicvf *nic, - struct cmp_queue *cq, struct cqe_rx_t *cqe_rx); +int nicvf_check_cqe_rx_errs(struct nicvf *nic, struct cqe_rx_t *cqe_rx); int nicvf_check_cqe_tx_errs(struct nicvf *nic, struct cmp_queue *cq, struct cqe_send_t *cqe_tx); #endif /* NICVF_QUEUES_H */ From 562a9f91a0300ecaaf28722f57bcdd9cd5f38f0e Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Mon, 15 Feb 2016 21:23:47 -0500 Subject: [PATCH 285/489] et131x: check return value of dma_alloc_coherent For error handling, dma_alloc_coherent's return value needs to be checked, not argument. Signed-off-by: Insu Yun Signed-off-by: David S. Miller --- drivers/net/ethernet/agere/et131x.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index 3f3bcbea15bd..0907ab6ff309 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2380,7 +2380,7 @@ static int et131x_tx_dma_memory_alloc(struct et131x_adapter *adapter) sizeof(u32), &tx_ring->tx_status_pa, GFP_KERNEL); - if (!tx_ring->tx_status_pa) { + if (!tx_ring->tx_status) { dev_err(&adapter->pdev->dev, "Cannot alloc memory for Tx status block\n"); return -ENOMEM; From f4eafd8bcd5229e998aa252627703b8462c3b90f Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 17 Feb 2016 18:16:54 -0700 Subject: [PATCH 286/489] x86/mm: Fix vmalloc_fault() to handle large pages properly A kernel page fault oops with the callstack below was observed when a read syscall was made to a pmem device after a huge amount (>512GB) of vmalloc ranges was allocated by ioremap() on a x86_64 system: BUG: unable to handle kernel paging request at ffff880840000ff8 IP: vmalloc_fault+0x1be/0x300 PGD c7f03a067 PUD 0 Oops: 0000 [#1] SM Call Trace: __do_page_fault+0x285/0x3e0 do_page_fault+0x2f/0x80 ? put_prev_entity+0x35/0x7a0 page_fault+0x28/0x30 ? memcpy_erms+0x6/0x10 ? schedule+0x35/0x80 ? pmem_rw_bytes+0x6a/0x190 [nd_pmem] ? schedule_timeout+0x183/0x240 btt_log_read+0x63/0x140 [nd_btt] : ? __symbol_put+0x60/0x60 ? kernel_read+0x50/0x80 SyS_finit_module+0xb9/0xf0 entry_SYSCALL_64_fastpath+0x1a/0xa4 Since v4.1, ioremap() supports large page (pud/pmd) mappings in x86_64 and PAE. vmalloc_fault() however assumes that the vmalloc range is limited to pte mappings. vmalloc faults do not normally happen in ioremap'd ranges since ioremap() sets up the kernel page tables, which are shared by user processes. pgd_ctor() sets the kernel's PGD entries to user's during fork(). When allocation of the vmalloc ranges crosses a 512GB boundary, ioremap() allocates a new pud table and updates the kernel PGD entry to point it. If user process's PGD entry does not have this update yet, a read/write syscall to the range will cause a vmalloc fault, which hits the Oops above as it does not handle a large page properly. Following changes are made to vmalloc_fault(). 64-bit: - No change for the PGD sync operation as it handles large pages already. - Add pud_huge() and pmd_huge() to the validation code to handle large pages. - Change pud_page_vaddr() to pud_pfn() since an ioremap range is not directly mapped (while the if-statement still works with a bogus addr). - Change pmd_page() to pmd_pfn() since an ioremap range is not backed by struct page (while the if-statement still works with a bogus addr). 32-bit: - No change for the sync operation since the index3 PGD entry covers the entire vmalloc range, which is always valid. (A separate change to sync PGD entry is necessary if this memory layout is changed regardless of the page size.) - Add pmd_huge() to the validation code to handle large pages. This is for completeness since vmalloc_fault() won't happen in ioremap'd ranges as its PGD entry is always valid. Reported-by: Henning Schild Signed-off-by: Toshi Kani Acked-by: Borislav Petkov Cc: # 4.1+ Cc: Andrew Morton Cc: Andy Lutomirski Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Luis R. Rodriguez Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Toshi Kani Cc: linux-mm@kvack.org Cc: linux-nvdimm@lists.01.org Link: http://lkml.kernel.org/r/1455758214-24623-1-git-send-email-toshi.kani@hpe.com Signed-off-by: Ingo Molnar --- arch/x86/mm/fault.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index eef44d9a3f77..e830c71a1323 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -287,6 +287,9 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; + if (pmd_huge(*pmd_k)) + return 0; + pte_k = pte_offset_kernel(pmd_k, address); if (!pte_present(*pte_k)) return -1; @@ -360,8 +363,6 @@ void vmalloc_sync_all(void) * 64-bit: * * Handle a fault on the vmalloc area - * - * This assumes no large pages in there. */ static noinline int vmalloc_fault(unsigned long address) { @@ -403,17 +404,23 @@ static noinline int vmalloc_fault(unsigned long address) if (pud_none(*pud_ref)) return -1; - if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref)) + if (pud_none(*pud) || pud_pfn(*pud) != pud_pfn(*pud_ref)) BUG(); + if (pud_huge(*pud)) + return 0; + pmd = pmd_offset(pud, address); pmd_ref = pmd_offset(pud_ref, address); if (pmd_none(*pmd_ref)) return -1; - if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref)) + if (pmd_none(*pmd) || pmd_pfn(*pmd) != pmd_pfn(*pmd_ref)) BUG(); + if (pmd_huge(*pmd)) + return 0; + pte_ref = pte_offset_kernel(pmd_ref, address); if (!pte_present(*pte_ref)) return -1; From 67ec1072b053c15564e6090ab30127895dc77a89 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 17 Feb 2016 14:30:26 +0100 Subject: [PATCH 287/489] ALSA: pcm: Fix rwsem deadlock for non-atomic PCM stream A non-atomic PCM stream may take snd_pcm_link_rwsem rw semaphore twice in the same code path, e.g. one in snd_pcm_action_nonatomic() and another in snd_pcm_stream_lock(). Usually this is OK, but when a write lock is issued between these two read locks, the problem happens: the write lock is blocked due to the first reade lock, and the second read lock is also blocked by the write lock. This eventually deadlocks. The reason is the way rwsem manages waiters; it's queued like FIFO, so even if the writer itself doesn't take the lock yet, it blocks all the waiters (including reads) queued after it. As a workaround, in this patch, we replace the standard down_write() with an spinning loop. This is far from optimal, but it's good enough, as the spinning time is supposed to be relatively short for normal PCM operations, and the code paths requiring the write lock aren't called so often. Reported-by: Vinod Koul Tested-by: Ramesh Babu Cc: # v3.18+ Signed-off-by: Takashi Iwai --- sound/core/pcm_native.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c index fadd3eb8e8bb..9106d8e2300e 100644 --- a/sound/core/pcm_native.c +++ b/sound/core/pcm_native.c @@ -74,6 +74,18 @@ static int snd_pcm_open(struct file *file, struct snd_pcm *pcm, int stream); static DEFINE_RWLOCK(snd_pcm_link_rwlock); static DECLARE_RWSEM(snd_pcm_link_rwsem); +/* Writer in rwsem may block readers even during its waiting in queue, + * and this may lead to a deadlock when the code path takes read sem + * twice (e.g. one in snd_pcm_action_nonatomic() and another in + * snd_pcm_stream_lock()). As a (suboptimal) workaround, let writer to + * spin until it gets the lock. + */ +static inline void down_write_nonblock(struct rw_semaphore *lock) +{ + while (!down_write_trylock(lock)) + cond_resched(); +} + /** * snd_pcm_stream_lock - Lock the PCM stream * @substream: PCM substream @@ -1813,7 +1825,7 @@ static int snd_pcm_link(struct snd_pcm_substream *substream, int fd) res = -ENOMEM; goto _nolock; } - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (substream->runtime->status->state == SNDRV_PCM_STATE_OPEN || substream->runtime->status->state != substream1->runtime->status->state || @@ -1860,7 +1872,7 @@ static int snd_pcm_unlink(struct snd_pcm_substream *substream) struct snd_pcm_substream *s; int res = 0; - down_write(&snd_pcm_link_rwsem); + down_write_nonblock(&snd_pcm_link_rwsem); write_lock_irq(&snd_pcm_link_rwlock); if (!snd_pcm_stream_linked(substream)) { res = -EALREADY; From 3158a8d416f4e1b79dcc867d67cb50013140772c Mon Sep 17 00:00:00 2001 From: Andrey Skvortsov Date: Fri, 29 Jan 2016 00:07:30 +0300 Subject: [PATCH 288/489] USB: option: add support for SIM7100E $ lsusb: Bus 001 Device 101: ID 1e0e:9001 Qualcomm / Option $ usb-devices: T: Bus=01 Lev=02 Prnt=02 Port=00 Cnt=01 Dev#=101 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 2 P: Vendor=1e0e ProdID=9001 Rev= 2.32 S: Manufacturer=SimTech, Incorporated S: Product=SimTech, Incorporated S: SerialNumber=0123456789ABCDEF C:* #Ifs= 7 Cfg#= 1 Atr=80 MxPwr=500mA I:* If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I:* If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=00 Prot=00 Driver=option I:* If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I:* If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none) The last interface (6) is used for Android Composite ADB interface. Serial port layout: 0: QCDM/DIAG 1: NMEA 2: AT 3: AT/PPP 4: audio Signed-off-by: Andrey Skvortsov Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index db86e512e0fc..e7eb08d56bae 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -315,6 +315,7 @@ static void option_instat_callback(struct urb *urb); #define TOSHIBA_PRODUCT_G450 0x0d45 #define ALINK_VENDOR_ID 0x1e0e +#define SIMCOM_PRODUCT_SIM7100E 0x9001 /* Yes, ALINK_VENDOR_ID */ #define ALINK_PRODUCT_PH300 0x9100 #define ALINK_PRODUCT_3GU 0x9200 @@ -607,6 +608,10 @@ static const struct option_blacklist_info zte_1255_blacklist = { .reserved = BIT(3) | BIT(4), }; +static const struct option_blacklist_info simcom_sim7100e_blacklist = { + .reserved = BIT(5) | BIT(6), +}; + static const struct option_blacklist_info telit_le910_blacklist = { .sendsetup = BIT(0), .reserved = BIT(1) | BIT(2), @@ -1645,6 +1650,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(ALINK_VENDOR_ID, 0x9000) }, { USB_DEVICE(ALINK_VENDOR_ID, ALINK_PRODUCT_PH300) }, { USB_DEVICE_AND_INTERFACE_INFO(ALINK_VENDOR_ID, ALINK_PRODUCT_3GU, 0xff, 0xff, 0xff) }, + { USB_DEVICE(ALINK_VENDOR_ID, SIMCOM_PRODUCT_SIM7100E), + .driver_info = (kernel_ulong_t)&simcom_sim7100e_blacklist }, { USB_DEVICE(ALCATEL_VENDOR_ID, ALCATEL_PRODUCT_X060S_X200), .driver_info = (kernel_ulong_t)&alcatel_x200_blacklist }, From 6627ae19385283b89356a199d7f03c75ba35fb29 Mon Sep 17 00:00:00 2001 From: Ken Lin Date: Mon, 1 Feb 2016 14:57:25 -0500 Subject: [PATCH 289/489] USB: cp210x: add IDs for GE B650V3 and B850V3 boards Add USB ID for cp2104/5 devices on GE B650v3 and B850v3 boards. Signed-off-by: Ken Lin Signed-off-by: Akshay Bhat Cc: stable Signed-off-by: Johan Hovold --- drivers/usb/serial/cp210x.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c index 987813b8a7f9..7c319e7edda2 100644 --- a/drivers/usb/serial/cp210x.c +++ b/drivers/usb/serial/cp210x.c @@ -163,6 +163,8 @@ static const struct usb_device_id id_table[] = { { USB_DEVICE(0x1843, 0x0200) }, /* Vaisala USB Instrument Cable */ { USB_DEVICE(0x18EF, 0xE00F) }, /* ELV USB-I2C-Interface */ { USB_DEVICE(0x18EF, 0xE025) }, /* ELV Marble Sound Board 1 */ + { USB_DEVICE(0x1901, 0x0190) }, /* GE B850 CP2105 Recorder interface */ + { USB_DEVICE(0x1901, 0x0193) }, /* GE B650 CP2104 PMC interface */ { USB_DEVICE(0x1ADB, 0x0001) }, /* Schweitzer Engineering C662 Cable */ { USB_DEVICE(0x1B1C, 0x1C00) }, /* Corsair USB Dongle */ { USB_DEVICE(0x1BA4, 0x0002) }, /* Silicon Labs 358x factory default */ From 0eca6fdb3193410fbe66b6f064431cc394513e82 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 16 Feb 2016 09:42:57 +0530 Subject: [PATCH 290/489] ARC: Assume multiplier is always present It is unlikely that designs running Linux will not have multiplier. Further the current support is not complete as tool don't generate a multilib w/o multiplier. Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 8 -------- arch/arc/Makefile | 4 ---- arch/arc/kernel/setup.c | 2 -- 3 files changed, 14 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0655495470ad..0f8df0aa2eb8 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -275,14 +275,6 @@ config ARC_DCCM_BASE default "0xA0000000" depends on ARC_HAS_DCCM -config ARC_HAS_HW_MPY - bool "Use Hardware Multiplier (Normal or Faster XMAC)" - default y - help - Influences how gcc generates code for MPY operations. - If enabled, MPYxx insns are generated, provided by Standard/XMAC - Multipler. Otherwise software multipy lib is used - choice prompt "MMU Version" default ARC_MMU_V3 if ARC_CPU_770 diff --git a/arch/arc/Makefile b/arch/arc/Makefile index aeb19021099e..c8230f3395f2 100644 --- a/arch/arc/Makefile +++ b/arch/arc/Makefile @@ -74,10 +74,6 @@ ldflags-$(CONFIG_CPU_BIG_ENDIAN) += -EB # --build-id w/o "-marclinux". Default arc-elf32-ld is OK ldflags-$(upto_gcc44) += -marclinux -ifndef CONFIG_ARC_HAS_HW_MPY - cflags-y += -mno-mpy -endif - LIBGCC := $(shell $(CC) $(cflags-y) --print-libgcc-file-name) # Modules with short calls might break for calls into builtin-kernel diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index a7edceba5f84..28dba569edd4 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -237,8 +237,6 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len) n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt); } - n += scnprintf(buf + n, len - n, "%s", - IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY)); } n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n", From 98341f7dc9d9080d7999654ab589657272559b04 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Mon, 15 Feb 2016 15:58:42 +0530 Subject: [PATCH 291/489] ARCv2: boot print Low Latency Memory Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index bc771f58fefb..002c5fcf8947 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -111,10 +111,11 @@ static void mcip_probe_n_setup(void) READ_BCR(ARC_REG_MCIP_BCR, mp); sprintf(smp_cpuinfo_buf, - "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n", + "Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n", mp.ver, mp.num_cores, IS_AVAIL1(mp.ipi, "IPI "), IS_AVAIL1(mp.idu, "IDU "), + IS_AVAIL1(mp.llm, "LLM "), IS_AVAIL1(mp.dbg, "DEBUG "), IS_AVAIL1(mp.gfrc, "GFRC")); From a150b085b66c87bd4d362a523cb85ce2b0a2d77b Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 16 Feb 2016 12:36:18 +0530 Subject: [PATCH 292/489] ARCv2: boot report CCMs (Closely Coupled Memories) - ARCv2 uses a seperate BCR for {I,D}CCM base address: ARCompact encoded both base/size in same BCR - Size encoding in common BCR is different for ARCompact/ARCv2 Signed-off-by: Vineet Gupta --- arch/arc/include/asm/arcregs.h | 32 ++++++++------ arch/arc/kernel/setup.c | 78 ++++++++++++++++++++++------------ 2 files changed, 70 insertions(+), 40 deletions(-) diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h index fdc5be5b1029..f9f4c6f59fdb 100644 --- a/arch/arc/include/asm/arcregs.h +++ b/arch/arc/include/asm/arcregs.h @@ -10,7 +10,8 @@ #define _ASM_ARC_ARCREGS_H /* Build Configuration Registers */ -#define ARC_REG_DCCMBASE_BCR 0x61 /* DCCM Base Addr */ +#define ARC_REG_AUX_DCCM 0x18 /* DCCM Base Addr ARCv2 */ +#define ARC_REG_DCCM_BASE_BUILD 0x61 /* DCCM Base Addr ARCompact */ #define ARC_REG_CRC_BCR 0x62 #define ARC_REG_VECBASE_BCR 0x68 #define ARC_REG_PERIBASE_BCR 0x69 @@ -18,10 +19,10 @@ #define ARC_REG_DPFP_BCR 0x6C /* ARCompact: Dbl Precision FPU */ #define ARC_REG_FP_V2_BCR 0xc8 /* ARCv2 FPU */ #define ARC_REG_SLC_BCR 0xce -#define ARC_REG_DCCM_BCR 0x74 /* DCCM Present + SZ */ +#define ARC_REG_DCCM_BUILD 0x74 /* DCCM size (common) */ #define ARC_REG_TIMERS_BCR 0x75 #define ARC_REG_AP_BCR 0x76 -#define ARC_REG_ICCM_BCR 0x78 +#define ARC_REG_ICCM_BUILD 0x78 /* ICCM size (common) */ #define ARC_REG_XY_MEM_BCR 0x79 #define ARC_REG_MAC_BCR 0x7a #define ARC_REG_MUL_BCR 0x7b @@ -36,6 +37,7 @@ #define ARC_REG_IRQ_BCR 0xF3 #define ARC_REG_SMART_BCR 0xFF #define ARC_REG_CLUSTER_BCR 0xcf +#define ARC_REG_AUX_ICCM 0x208 /* ICCM Base Addr (ARCv2) */ /* status32 Bits Positions */ #define STATUS_AE_BIT 5 /* Exception active */ @@ -246,7 +248,7 @@ struct bcr_perip { #endif }; -struct bcr_iccm { +struct bcr_iccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int base:16, pad:5, sz:3, ver:8; #else @@ -254,17 +256,15 @@ struct bcr_iccm { #endif }; -/* DCCM Base Address Register: ARC_REG_DCCMBASE_BCR */ -struct bcr_dccm_base { +struct bcr_iccm_arcv2 { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int addr:24, ver:8; + unsigned int pad:8, sz11:4, sz01:4, sz10:4, sz00:4, ver:8; #else - unsigned int ver:8, addr:24; + unsigned int ver:8, sz00:4, sz10:4, sz01:4, sz11:4, pad:8; #endif }; -/* DCCM RAM Configuration Register: ARC_REG_DCCM_BCR */ -struct bcr_dccm { +struct bcr_dccm_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN unsigned int res:21, sz:3, ver:8; #else @@ -272,6 +272,14 @@ struct bcr_dccm { #endif }; +struct bcr_dccm_arcv2 { +#ifdef CONFIG_CPU_BIG_ENDIAN + unsigned int pad2:12, cyc:3, pad1:1, sz1:4, sz0:4, ver:8; +#else + unsigned int ver:8, sz0:4, sz1:4, pad1:1, cyc:3, pad2:12; +#endif +}; + /* ARCompact: Both SP and DP FPU BCRs have same format */ struct bcr_fp_arcompact { #ifdef CONFIG_CPU_BIG_ENDIAN @@ -315,9 +323,9 @@ struct bcr_bpu_arcv2 { struct bcr_generic { #ifdef CONFIG_CPU_BIG_ENDIAN - unsigned int pad:24, ver:8; + unsigned int info:24, ver:8; #else - unsigned int ver:8, pad:24; + unsigned int ver:8, info:24; #endif }; diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c index 28dba569edd4..cdc821df1809 100644 --- a/arch/arc/kernel/setup.c +++ b/arch/arc/kernel/setup.c @@ -42,6 +42,53 @@ struct task_struct *_current_task[NR_CPUS]; /* For stack switching */ struct cpuinfo_arc cpuinfo_arc700[NR_CPUS]; +static void read_decode_ccm_bcr(struct cpuinfo_arc *cpu) +{ + if (is_isa_arcompact()) { + struct bcr_iccm_arcompact iccm; + struct bcr_dccm_arcompact dccm; + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + cpu->iccm.sz = 4096 << iccm.sz; /* 8K to 512K */ + cpu->iccm.base_addr = iccm.base << 16; + } + + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + unsigned long base; + cpu->dccm.sz = 2048 << dccm.sz; /* 2K to 256K */ + + base = read_aux_reg(ARC_REG_DCCM_BASE_BUILD); + cpu->dccm.base_addr = base & ~0xF; + } + } else { + struct bcr_iccm_arcv2 iccm; + struct bcr_dccm_arcv2 dccm; + unsigned long region; + + READ_BCR(ARC_REG_ICCM_BUILD, iccm); + if (iccm.ver) { + cpu->iccm.sz = 256 << iccm.sz00; /* 512B to 16M */ + if (iccm.sz00 == 0xF && iccm.sz01 > 0) + cpu->iccm.sz <<= iccm.sz01; + + region = read_aux_reg(ARC_REG_AUX_ICCM); + cpu->iccm.base_addr = region & 0xF0000000; + } + + READ_BCR(ARC_REG_DCCM_BUILD, dccm); + if (dccm.ver) { + cpu->dccm.sz = 256 << dccm.sz0; + if (dccm.sz0 == 0xF && dccm.sz1 > 0) + cpu->dccm.sz <<= dccm.sz1; + + region = read_aux_reg(ARC_REG_AUX_DCCM); + cpu->dccm.base_addr = region & 0xF0000000; + } + } +} + static void read_arc_build_cfg_regs(void) { struct bcr_perip uncached_space; @@ -76,36 +123,11 @@ static void read_arc_build_cfg_regs(void) cpu->extn.swap = read_aux_reg(ARC_REG_SWAP_BCR) ? 1 : 0; /* 1,3 */ cpu->extn.crc = read_aux_reg(ARC_REG_CRC_BCR) ? 1 : 0; cpu->extn.minmax = read_aux_reg(ARC_REG_MIXMAX_BCR) > 1 ? 1 : 0; /* 2 */ - - /* Note that we read the CCM BCRs independent of kernel config - * This is to catch the cases where user doesn't know that - * CCMs are present in hardware build - */ - { - struct bcr_iccm iccm; - struct bcr_dccm dccm; - struct bcr_dccm_base dccm_base; - unsigned int bcr_32bit_val; - - bcr_32bit_val = read_aux_reg(ARC_REG_ICCM_BCR); - if (bcr_32bit_val) { - iccm = *((struct bcr_iccm *)&bcr_32bit_val); - cpu->iccm.base_addr = iccm.base << 16; - cpu->iccm.sz = 0x2000 << (iccm.sz - 1); - } - - bcr_32bit_val = read_aux_reg(ARC_REG_DCCM_BCR); - if (bcr_32bit_val) { - dccm = *((struct bcr_dccm *)&bcr_32bit_val); - cpu->dccm.sz = 0x800 << (dccm.sz); - - READ_BCR(ARC_REG_DCCMBASE_BCR, dccm_base); - cpu->dccm.base_addr = dccm_base.addr << 8; - } - } - READ_BCR(ARC_REG_XY_MEM_BCR, cpu->extn_xymem); + /* Read CCM BCRs for boot reporting even if not enabled in Kconfig */ + read_decode_ccm_bcr(cpu); + read_decode_mmu_bcr(); read_decode_cache_bcr(); From d061c1caa31d4d9792cfe48a2c6b309a0e01ef46 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Fri, 12 Feb 2016 16:40:00 +0100 Subject: [PATCH 293/489] USB: option: add "4G LTE usb-modem U901" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Thomas reports: T: Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0 D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1 P: Vendor=05c6 ProdID=6001 Rev=00.00 S: Manufacturer=USB Modem S: Product=USB Modem S: SerialNumber=1234567890ABCDEF C: #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=500mA I: If#= 0 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 2 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=ff Driver=option I: If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=ff Driver=qmi_wwan I: If#= 4 Alt= 0 #EPs= 2 Cls=08(stor.) Sub=06 Prot=50 Driver=usb-storage Cc: Reported-by: Thomas Schäfer Signed-off-by: Bjørn Mork Signed-off-by: Johan Hovold --- drivers/usb/serial/option.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index e7eb08d56bae..8849439a8f18 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1127,6 +1127,8 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC650) }, { USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */ + { USB_DEVICE_AND_INTERFACE_INFO(QUALCOMM_VENDOR_ID, 0x6001, 0xff, 0xff, 0xff), /* 4G LTE usb-modem U901 */ + .driver_info = (kernel_ulong_t)&net_intf3_blacklist }, { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x0023)}, /* ONYX 3G device */ { USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */ From 1a1503c5396eb7f2edf4b8ef6067853014478c0c Mon Sep 17 00:00:00 2001 From: Alexandra Yates Date: Wed, 17 Feb 2016 18:21:21 -0800 Subject: [PATCH 294/489] i2c: i801: Adding Intel Lewisburg support for iTCO Starting from Intel Sunrisepoint (Skylake PCH) the iTCO watchdog resources have been moved to reside under the i801 SMBus host controller whereas previously they were under the LPC device. This patch adds Intel lewisburg SMBus support for iTCO device. It allows to load watchdog dynamically when the hardware is present. Fixes: cdc5a3110e7c ("i2c: i801: add Intel Lewisburg device IDs") Reviewed-by: Jean Delvare Signed-off-by: Alexandra Yates Signed-off-by: Wolfram Sang Cc: stable@kernel.org --- drivers/i2c/busses/i2c-i801.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index f62d69799a9c..27fa0cb09538 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1271,6 +1271,8 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id) switch (dev->device) { case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS: case PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS: + case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS: + case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS: case PCI_DEVICE_ID_INTEL_DNV_SMBUS: priv->features |= FEATURE_I2C_BLOCK_READ; priv->features |= FEATURE_IRQ; From 148f472da5db4d78fcfe61807c18f020eb5bd7fc Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 18 Feb 2016 11:30:01 +0100 Subject: [PATCH 295/489] mlxsw: reg: Add the Switch Port Acceptable Frame Types register When VLAN filtering is enabled on a bridge and PVID is deleted from a bridge port, then untagged frames are not allowed to ingress into the bridge from this port. Add the Switch Port Acceptable Frame Types (SPAFT) register, which configures the frame admittance of the port. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/reg.h | 58 +++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index bb77e2207804..ffe4c0305733 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -873,6 +873,62 @@ static inline void mlxsw_reg_spvm_pack(char *payload, u8 local_port, } } +/* SPAFT - Switch Port Acceptable Frame Types + * ------------------------------------------ + * The Switch Port Acceptable Frame Types register configures the frame + * admittance of the port. + */ +#define MLXSW_REG_SPAFT_ID 0x2010 +#define MLXSW_REG_SPAFT_LEN 0x08 + +static const struct mlxsw_reg_info mlxsw_reg_spaft = { + .id = MLXSW_REG_SPAFT_ID, + .len = MLXSW_REG_SPAFT_LEN, +}; + +/* reg_spaft_local_port + * Local port number. + * Access: Index + * + * Note: CPU port is not supported (all tag types are allowed). + */ +MLXSW_ITEM32(reg, spaft, local_port, 0x00, 16, 8); + +/* reg_spaft_sub_port + * Virtual port within the physical port. + * Should be set to 0 when virtual ports are not enabled on the port. + * Access: RW + */ +MLXSW_ITEM32(reg, spaft, sub_port, 0x00, 8, 8); + +/* reg_spaft_allow_untagged + * When set, untagged frames on the ingress are allowed (default). + * Access: RW + */ +MLXSW_ITEM32(reg, spaft, allow_untagged, 0x04, 31, 1); + +/* reg_spaft_allow_prio_tagged + * When set, priority tagged frames on the ingress are allowed (default). + * Access: RW + */ +MLXSW_ITEM32(reg, spaft, allow_prio_tagged, 0x04, 30, 1); + +/* reg_spaft_allow_tagged + * When set, tagged frames on the ingress are allowed (default). + * Access: RW + */ +MLXSW_ITEM32(reg, spaft, allow_tagged, 0x04, 29, 1); + +static inline void mlxsw_reg_spaft_pack(char *payload, u8 local_port, + bool allow_untagged) +{ + MLXSW_REG_ZERO(spaft, payload); + mlxsw_reg_spaft_local_port_set(payload, local_port); + mlxsw_reg_spaft_allow_untagged_set(payload, allow_untagged); + mlxsw_reg_spaft_allow_prio_tagged_set(payload, true); + mlxsw_reg_spaft_allow_tagged_set(payload, true); +} + /* SFGC - Switch Flooding Group Configuration * ------------------------------------------ * The following register controls the association of flooding tables and MIDs @@ -3203,6 +3259,8 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id) return "SPVID"; case MLXSW_REG_SPVM_ID: return "SPVM"; + case MLXSW_REG_SPAFT_ID: + return "SPAFT"; case MLXSW_REG_SFGC_ID: return "SFGC"; case MLXSW_REG_SFTR_ID: From 28a01d2d7dbf6d56e6130b3094b7c62a54773f27 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 18 Feb 2016 11:30:02 +0100 Subject: [PATCH 296/489] mlxsw: spectrum: Allow for PVID deletion When PVID is toggled off on a port member in a VLAN filtering bridge or the PVID VLAN is deleted, make the port drop untagged packets. Reverse the operation when PVID is toggled back on. Set the PVID back to the default (1), when leaving the bridge so that untagged traffic will be directed to the CPU. Fixes: 56ade8fe3fe1 ("mlxsw: spectrum: Add initial support for Spectrum ASIC") Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- .../net/ethernet/mellanox/mlxsw/spectrum.c | 2 + .../net/ethernet/mellanox/mlxsw/spectrum.h | 1 + .../mellanox/mlxsw/spectrum_switchdev.c | 69 ++++++++++++++++--- 3 files changed, 63 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 0fa8da584845..09ce451c283b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2123,6 +2123,8 @@ static int mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, if (flush_fdb && mlxsw_sp_port_fdb_flush(mlxsw_sp_port)) netdev_err(mlxsw_sp_port->dev, "Failed to flush FDB\n"); + mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1); + mlxsw_sp_port->learning = 0; mlxsw_sp_port->learning_sync = 0; mlxsw_sp_port->uc_flood = 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 7f42eb1c320e..3b89ed2f3c76 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -254,5 +254,6 @@ int mlxsw_sp_port_kill_vid(struct net_device *dev, int mlxsw_sp_vport_flood_set(struct mlxsw_sp_port *mlxsw_sp_vport, u16 vfid, bool set, bool only_uc); void mlxsw_sp_port_active_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port); +int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid); #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index e492ca2cdecd..7b56098acc58 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -370,7 +370,8 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, return err; } -static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) +static int __mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, + u16 vid) { struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; char spvid_pl[MLXSW_REG_SPVID_LEN]; @@ -379,6 +380,53 @@ static int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spvid), spvid_pl); } +static int mlxsw_sp_port_allow_untagged_set(struct mlxsw_sp_port *mlxsw_sp_port, + bool allow) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char spaft_pl[MLXSW_REG_SPAFT_LEN]; + + mlxsw_reg_spaft_pack(spaft_pl, mlxsw_sp_port->local_port, allow); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(spaft), spaft_pl); +} + +int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid) +{ + struct net_device *dev = mlxsw_sp_port->dev; + int err; + + if (!vid) { + err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port, false); + if (err) { + netdev_err(dev, "Failed to disallow untagged traffic\n"); + return err; + } + } else { + err = __mlxsw_sp_port_pvid_set(mlxsw_sp_port, vid); + if (err) { + netdev_err(dev, "Failed to set PVID\n"); + return err; + } + + /* Only allow if not already allowed. */ + if (!mlxsw_sp_port->pvid) { + err = mlxsw_sp_port_allow_untagged_set(mlxsw_sp_port, + true); + if (err) { + netdev_err(dev, "Failed to allow untagged traffic\n"); + goto err_port_allow_untagged_set; + } + } + } + + mlxsw_sp_port->pvid = vid; + return 0; + +err_port_allow_untagged_set: + __mlxsw_sp_port_pvid_set(mlxsw_sp_port, mlxsw_sp_port->pvid); + return err; +} + static int mlxsw_sp_fid_create(struct mlxsw_sp *mlxsw_sp, u16 fid) { char sfmr_pl[MLXSW_REG_SFMR_LEN]; @@ -540,7 +588,12 @@ static int __mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port, netdev_err(dev, "Unable to add PVID %d\n", vid_begin); goto err_port_pvid_set; } - mlxsw_sp_port->pvid = vid_begin; + } else if (!flag_pvid && old_pvid >= vid_begin && old_pvid <= vid_end) { + err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0); + if (err) { + netdev_err(dev, "Unable to del PVID\n"); + goto err_port_pvid_set; + } } /* Changing activity bits only if HW operation succeded */ @@ -892,20 +945,18 @@ static int __mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port, return err; } + if (init) + goto out; + pvid = mlxsw_sp_port->pvid; - if (pvid >= vid_begin && pvid <= vid_end && pvid != 1) { - /* Default VLAN is always 1 */ - err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1); + if (pvid >= vid_begin && pvid <= vid_end) { + err = mlxsw_sp_port_pvid_set(mlxsw_sp_port, 0); if (err) { netdev_err(dev, "Unable to del PVID %d\n", pvid); return err; } - mlxsw_sp_port->pvid = 1; } - if (init) - goto out; - err = __mlxsw_sp_port_flood_set(mlxsw_sp_port, vid_begin, vid_end, false, false); if (err) { From 619fe32640b4b01f370574d50344ae0f62689816 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Thu, 18 Feb 2016 07:38:04 -0500 Subject: [PATCH 297/489] net_sched fix: reclassification needs to consider ether protocol changes actions could change the etherproto in particular with ethernet tunnelled data. Typically such actions, after peeling the outer header, will ask for the packet to be reclassified. We then need to restart the classification with the new proto header. Example setup used to catch this: sudo tc qdisc add dev $ETH ingress sudo $TC filter add dev $ETH parent ffff: pref 1 protocol 802.1Q \ u32 match u32 0 0 flowid 1:1 \ action vlan pop reclassify Fixes: 3b3ae880266d ("net: sched: consolidate tc_classify{,_compat}") Signed-off-by: Jamal Hadi Salim Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/sched/sch_api.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b5c2cf2aa6d4..af1acf009866 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1852,6 +1852,7 @@ reset: } tp = old_tp; + protocol = tc_skb_protocol(skb); goto reclassify; #endif } From deed49df7390d5239024199e249190328f1651e7 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Thu, 18 Feb 2016 21:21:19 +0800 Subject: [PATCH 298/489] route: check and remove route cache when we get route Since the gc of ipv4 route was removed, the route cached would has no chance to be removed, and even it has been timeout, it still could be used, cause no code to check it's expires. Fix this issue by checking and removing route cache when we get route. Signed-off-by: Xin Long Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/net/ip_fib.h | 1 + net/ipv4/route.c | 77 ++++++++++++++++++++++++++++++++++++-------- 2 files changed, 64 insertions(+), 14 deletions(-) diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 7029527725dd..4079fc18ffe4 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -61,6 +61,7 @@ struct fib_nh_exception { struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; + struct rcu_head rcu; }; struct fnhe_hash_bucket { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 85f184e429c6..02c62299d717 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; +static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ @@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow struct fib_nh *nh = &FIB_RES_NH(res); update_or_create_fnhe(nh, fl4->daddr, new_gw, - 0, 0); + 0, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; @@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, @@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) + if (fnhe) { rth = rcu_dereference(fnhe->fnhe_rth_input); - else - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(&FIB_RES_NH(*res), daddr); + fnhe = NULL; + } else { + goto rt_cache; + } + } + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); + +rt_cache: if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res, struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); - if (fnhe) + if (fnhe) { prth = &fnhe->fnhe_rth_output; - else { - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; + rth = rcu_dereference(*prth); + if (rth && rth->dst.expires && + time_after(jiffies, rth->dst.expires)) { + ip_del_fnhe(nh, fl4->daddr); + fnhe = NULL; + } else { + goto rt_cache; } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } + + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; + } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); + +rt_cache: if (rt_cache_valid(rth)) { dst_hold(&rth->dst); return rth; @@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev) } #ifdef CONFIG_SYSCTL -static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; From 7716682cc58e305e22207d5bb315f26af6b1e243 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Feb 2016 05:39:18 -0800 Subject: [PATCH 299/489] tcp/dccp: fix another race at listener dismantle Ilya reported following lockdep splat: kernel: ========================= kernel: [ BUG: held lock freed! ] kernel: 4.5.0-rc1-ceph-00026-g5e0a311 #1 Not tainted kernel: ------------------------- kernel: swapper/5/0 is freeing memory ffff880035c9d200-ffff880035c9dbff, with a lock still held there! kernel: (&(&queue->rskq_lock)->rlock){+.-...}, at: [] inet_csk_reqsk_queue_add+0x28/0xa0 kernel: 4 locks held by swapper/5/0: kernel: #0: (rcu_read_lock){......}, at: [] netif_receive_skb_internal+0x4b/0x1f0 kernel: #1: (rcu_read_lock){......}, at: [] ip_local_deliver_finish+0x3f/0x380 kernel: #2: (slock-AF_INET){+.-...}, at: [] sk_clone_lock+0x19b/0x440 kernel: #3: (&(&queue->rskq_lock)->rlock){+.-...}, at: [] inet_csk_reqsk_queue_add+0x28/0xa0 To properly fix this issue, inet_csk_reqsk_queue_add() needs to return to its callers if the child as been queued into accept queue. We also need to make sure listener is still there before calling sk->sk_data_ready(), by holding a reference on it, since the reference carried by the child can disappear as soon as the child is put on accept queue. Reported-by: Ilya Dryomov Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 5 +++-- net/dccp/ipv4.c | 14 +++++++------- net/dccp/ipv6.c | 14 +++++++------- net/ipv4/inet_connection_sock.c | 14 +++++++------- net/ipv4/tcp_ipv4.c | 14 +++++++------- net/ipv6/tcp_ipv6.c | 14 +++++++------- 6 files changed, 38 insertions(+), 37 deletions(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 481fe1c9044c..49dcad4fe99e 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -270,8 +270,9 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *newsk, const struct request_sock *req); -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child); +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child); void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 5684e14932bd..902d606324a0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -824,26 +824,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v4_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9c6d0508e63a..b8608b71a66d 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -691,26 +691,26 @@ lookup: if (sk->sk_state == DCCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; - if (likely(sk->sk_state == DCCP_LISTEN)) { - nsk = dccp_check_req(sk, skb, req); - } else { + if (unlikely(sk->sk_state != DCCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = dccp_check_req(sk, skb, req); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (dccp_child_process(sk, nsk, skb)) { dccp_v6_ctl_send_reset(sk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 46b9c887bede..64148914803a 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, reqsk_put(req); } -void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, - struct sock *child) +struct sock *inet_csk_reqsk_queue_add(struct sock *sk, + struct request_sock *req, + struct sock *child) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; spin_lock(&queue->rskq_lock); if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_child_forget(sk, req, child); + child = NULL; } else { req->sk = child; req->dl_next = NULL; @@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, sk_acceptq_added(sk); } spin_unlock(&queue->rskq_lock); + return child; } EXPORT_SYMBOL(inet_csk_reqsk_queue_add); @@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, if (own_req) { inet_csk_reqsk_queue_drop(sk, req); reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req); - inet_csk_reqsk_queue_add(sk, req, child); - /* Warning: caller must not call reqsk_put(req); - * child stole last reference on it. - */ - return child; + if (inet_csk_reqsk_queue_add(sk, req, child)) + return child; } /* Too bad, another child took ownership of the request, undo. */ bh_unlock_sock(child); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c84477949d3a..487ac67059e2 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1597,30 +1597,30 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1a5a70fb8551..5c8c84273028 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1387,7 +1387,7 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; tcp_v6_fill_cb(skb, hdr, th); @@ -1395,24 +1395,24 @@ process: reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); tcp_v6_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v6_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } From aeee0e66c6b46cee311be22cb82735763eceb7c3 Mon Sep 17 00:00:00 2001 From: David Wragg Date: Thu, 18 Feb 2016 17:43:29 +0000 Subject: [PATCH 300/489] geneve: Refine MTU limit Calculate the maximum MTU taking into account the size of headers involved in GENEVE encapsulation, as for other tunnel types. Changes in v3: - Correct comment style Changes in v2: - Conform more closely to ip_tunnel_change_mtu - Exclude GENEVE options from max MTU calculation Signed-off-by: David Wragg Acked-by: Jesse Gross Signed-off-by: David S. Miller --- drivers/net/geneve.c | 27 ++++++++++++++++++++++----- 1 file changed, 22 insertions(+), 5 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 028e3873c310..70975700f91d 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1039,17 +1039,34 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) return geneve_xmit_skb(skb, dev, info); } -static int geneve_change_mtu(struct net_device *dev, int new_mtu) +static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict) { - /* GENEVE overhead is not fixed, so we can't enforce a more - * precise max MTU. + /* The max_mtu calculation does not take account of GENEVE + * options, to avoid excluding potentially valid + * configurations. */ - if (new_mtu < 68 || new_mtu > IP_MAX_MTU) + int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - sizeof(struct iphdr) + - dev->hard_header_len; + + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +static int geneve_change_mtu(struct net_device *dev, int new_mtu) +{ + return __geneve_change_mtu(dev, new_mtu, true); +} + static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); @@ -1459,7 +1476,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ - err = geneve_change_mtu(dev, IP_MAX_MTU); + err = __geneve_change_mtu(dev, IP_MAX_MTU, false); if (err) goto err; From 8f318526a292c5e7cebb82f3f766b83c22343293 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 18 Feb 2016 19:15:45 +0000 Subject: [PATCH 301/489] irqchip/gic-v3: Add missing barrier to 32bit version of gic_read_iar() Commit 1a1ebd5 ("irqchip/gic-v3: Make sure read from ICC_IAR1_EL1 is visible on redestributor") fixed the missing barrier on arm64, but forgot to update the 32bit counterpart, which has the same requirements. Let's fix it. Fixes: 1a1ebd5 ("irqchip/gic-v3: Make sure read from ICC_IAR1_EL1 is visible on redestributor") Signed-off-by: Marc Zyngier --- arch/arm/include/asm/arch_gicv3.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h index 7da5503c0591..e08d15184056 100644 --- a/arch/arm/include/asm/arch_gicv3.h +++ b/arch/arm/include/asm/arch_gicv3.h @@ -117,6 +117,7 @@ static inline u32 gic_read_iar(void) u32 irqstat; asm volatile("mrc " __stringify(ICC_IAR1) : "=r" (irqstat)); + dsb(sy); return irqstat; } From 82a0f6b4aba95a21729f56ed0cbe57f2701b4872 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 16 Feb 2016 22:16:53 +0100 Subject: [PATCH 302/489] vxlan: clear IFF_TX_SKB_SHARING ether_setup sets IFF_TX_SKB_SHARING but this is not supported by vxlan as it modifies the skb on xmit. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index a31cd954b308..db96f3a16f6c 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2537,6 +2537,7 @@ static void vxlan_setup(struct net_device *dev) dev->hw_features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; netif_keep_dst(dev); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; INIT_LIST_HEAD(&vxlan->next); From fc41cdb322a2a513efd60f81133efecd69d4f336 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Wed, 17 Feb 2016 15:31:35 +0100 Subject: [PATCH 303/489] geneve: clear IFF_TX_SKB_SHARING ether_setup sets IFF_TX_SKB_SHARING but this is not supported by geneve as it modifies the skb on xmit. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/geneve.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 70975700f91d..4a9cc038c4b0 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1178,6 +1178,7 @@ static void geneve_setup(struct net_device *dev) dev->hw_features |= NETIF_F_GSO_SOFTWARE; netif_keep_dst(dev); + dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE; eth_hw_addr_random(dev); } From d13b161c2c7c67401bb222c30302339285ac148e Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Wed, 17 Feb 2016 15:32:53 +0100 Subject: [PATCH 304/489] gre: clear IFF_TX_SKB_SHARING ether_setup sets IFF_TX_SKB_SHARING but this is not supported by gre as it modifies the skb on xmit. Also, clean up whitespace in ipgre_tap_setup when we're already touching it. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 5 +++-- net/ipv6/ip6_gre.c | 1 + 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 56fdf4e0dce4..41ba68de46d8 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = { static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); - dev->netdev_ops = &gre_tap_netdev_ops; - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->netdev_ops = &gre_tap_netdev_ops; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index f37f18b6b40c..a69aad1e29d1 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1512,6 +1512,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->destructor = ip6gre_dev_free; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, From a813104d923339144078939175faf4e66aca19b4 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Wed, 17 Feb 2016 15:37:43 +0100 Subject: [PATCH 305/489] IFF_NO_QUEUE: Fix for drivers not calling ether_setup() My implementation around IFF_NO_QUEUE driver flag assumed that leaving tx_queue_len untouched (specifically: not setting it to zero) by drivers would make it possible to assign a regular qdisc to them without having to worry about setting tx_queue_len to a useful value. This was only partially true: I overlooked that some drivers don't call ether_setup() and therefore not initialize tx_queue_len to the default value of 1000. Consequently, removing the workarounds in place for that case in qdisc implementations which cared about it (namely, pfifo, bfifo, gred, htb, plug and sfb) leads to problems with these specific interface types and qdiscs. Luckily, there's already a sanitization point for drivers setting tx_queue_len to zero, which can be reused to assign the fallback value most qdisc implementations used, which is 1. Fixes: 348e3435cbefa ("net: sched: drop all special handling of tx_queue_len == 0") Tested-by: Mathieu Desnoyers Signed-off-by: Phil Sutter Signed-off-by: David S. Miller --- net/core/dev.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/core/dev.c b/net/core/dev.c index 8cba3d852f25..e15e6e6a7a8a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7422,8 +7422,10 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); - if (!dev->tx_queue_len) + if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; + dev->tx_queue_len = 1; + } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; From a09f4af177d2a5b7dc424aba6ba808f4a674ce81 Mon Sep 17 00:00:00 2001 From: Amitoj Kaur Chawla Date: Wed, 17 Feb 2016 20:33:26 +0530 Subject: [PATCH 306/489] lance: Return correct error code Failure of kzalloc should cause the enclosing function to return -ENOMEM, not -ENODEV. Additionally, removed the following checkpatch warnings: ERROR: spaces required around that '==' (ctx:VxV) ERROR: space required before the open parenthesis '(' CHECK: Comparison to NULL could be written "!lp" Signed-off-by: Amitoj Kaur Chawla Signed-off-by: David S. Miller --- drivers/net/ethernet/amd/lance.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/amd/lance.c b/drivers/net/ethernet/amd/lance.c index 256f590f6bb1..3a7ebfdda57d 100644 --- a/drivers/net/ethernet/amd/lance.c +++ b/drivers/net/ethernet/amd/lance.c @@ -547,8 +547,8 @@ static int __init lance_probe1(struct net_device *dev, int ioaddr, int irq, int /* Make certain the data structures used by the LANCE are aligned and DMAble. */ lp = kzalloc(sizeof(*lp), GFP_DMA | GFP_KERNEL); - if(lp==NULL) - return -ENODEV; + if (!lp) + return -ENOMEM; if (lance_debug > 6) printk(" (#0x%05lx)", (unsigned long)lp); dev->ml_priv = lp; lp->name = chipname; From 48bb230e8723d7dd87928f0c0c3f6cb1fd5bc9be Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 17 Feb 2016 10:53:59 -0500 Subject: [PATCH 307/489] appletalk: fix erroneous return value The atalk_sendmsg() function might return wrong value ENETUNREACH instead of -ENETUNREACH. Signed-off-by: Anton Protopopov Signed-off-by: David S. Miller --- net/appletalk/ddp.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index d5871ac493eb..f066781be3c8 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1625,7 +1625,7 @@ static int atalk_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) rt = atrtr_find(&at_hint); } - err = ENETUNREACH; + err = -ENETUNREACH; if (!rt) goto out; From 449f14f01f65f45f332e3360aa46b3d3571b2cba Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 17 Feb 2016 10:54:13 -0500 Subject: [PATCH 308/489] net: caif: fix erroneous return value The cfrfml_receive() function might return positive value EPROTO Signed-off-by: Anton Protopopov Signed-off-by: David S. Miller --- net/caif/cfrfml.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c index 61d7617d9249..b82440e1fcb4 100644 --- a/net/caif/cfrfml.c +++ b/net/caif/cfrfml.c @@ -159,7 +159,7 @@ static int cfrfml_receive(struct cflayer *layr, struct cfpkt *pkt) tmppkt = NULL; /* Verify that length is correct */ - err = EPROTO; + err = -EPROTO; if (rfml->pdu_size != cfpkt_getlen(pkt) - RFM_HEAD_SIZE + 1) goto out; } From e60b13e4f56fc56cc0dea845ce0711773d514149 Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Wed, 17 Feb 2016 11:19:56 -0500 Subject: [PATCH 309/489] mISDN: prevent possible NULL pointer dereference A return value of the bchannel_get_rxbuf() function is compared with the positive ENOMEM value instead of the negative -ENOMEM value to detect a memory allocation problem. Thus, after a possible memory allocation failure the bc->bch.rx_skb will be NULL which will lead to a NULL pointer dereference. Signed-off-by: Anton Protopopov Signed-off-by: David S. Miller --- drivers/isdn/hardware/mISDN/netjet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c index 8e2944784e00..afde4edef9ae 100644 --- a/drivers/isdn/hardware/mISDN/netjet.c +++ b/drivers/isdn/hardware/mISDN/netjet.c @@ -392,7 +392,7 @@ read_dma(struct tiger_ch *bc, u32 idx, int cnt) } stat = bchannel_get_rxbuf(&bc->bch, cnt); /* only transparent use the count here, HDLC overun is detected later */ - if (stat == ENOMEM) { + if (stat == -ENOMEM) { pr_warning("%s.B%d: No memory for %d bytes\n", card->name, bc->bch.nr, cnt); return; From f468a729a2ddb1a26f8c4b98a82050e4030fe458 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Tue, 16 Feb 2016 22:18:26 +0100 Subject: [PATCH 310/489] vxlan: do not use fdb in metadata mode In metadata mode, the vxlan interface is not supposed to use the fdb control plane but an external one (openvswitch or static routes). With the current code, packets may leak into the fdb handling code which usually causes them to be dropped anyway but may have strange side effects. Just drop the packets directly when in metadata mode if the destination data are not correctly provided on egress. Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index db96f3a16f6c..e6944b29588e 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2171,9 +2171,11 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev) #endif } - if (vxlan->flags & VXLAN_F_COLLECT_METADATA && - info && info->mode & IP_TUNNEL_INFO_TX) { - vxlan_xmit_one(skb, dev, NULL, false); + if (vxlan->flags & VXLAN_F_COLLECT_METADATA) { + if (info && info->mode & IP_TUNNEL_INFO_TX) + vxlan_xmit_one(skb, dev, NULL, false); + else + kfree_skb(skb); return NETDEV_TX_OK; } From f3bb23764fac042d189129d485d3a9246cb777da Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 17 Feb 2016 23:25:11 +0100 Subject: [PATCH 311/489] USB: cdc_subset: only build when one driver is enabled This avoids a harmless randconfig warning I get when USB_NET_CDC_SUBSET is enabled, but all of the more specific drivers are not: drivers/net/usb/cdc_subset.c:241:2: #warning You need to configure some hardware for this driver The current behavior is clearly intentional, giving a warning when a user picks a configuration that won't do anything good. The only reason for even addressing this is that I'm getting close to eliminating all 'randconfig' warnings on ARM, and this came up a couple of times. My workaround is to not even build the module when none of the configurations are enable. Alternatively we could simply remove the #warning (nothing wrong for compile-testing), turn it into a runtime warning, or change the Kconfig options into a menu to hide CONFIG_USB_NET_CDC_SUBSET. Signed-off-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/usb/Kconfig | 10 ++++++++++ drivers/net/usb/Makefile | 2 +- 2 files changed, 11 insertions(+), 1 deletion(-) diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index 7f83504dfa69..cdde59089f72 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -395,6 +395,10 @@ config USB_NET_RNDIS_HOST The protocol specification is incomplete, and is controlled by (and for) Microsoft; it isn't an "Open" ecosystem or market. +config USB_NET_CDC_SUBSET_ENABLE + tristate + depends on USB_NET_CDC_SUBSET + config USB_NET_CDC_SUBSET tristate "Simple USB Network Links (CDC Ethernet subset)" depends on USB_USBNET @@ -413,6 +417,7 @@ config USB_NET_CDC_SUBSET config USB_ALI_M5632 bool "ALi M5632 based 'USB 2.0 Data Link' cables" depends on USB_NET_CDC_SUBSET + select USB_NET_CDC_SUBSET_ENABLE help Choose this option if you're using a host-to-host cable based on this design, which supports USB 2.0 high speed. @@ -420,6 +425,7 @@ config USB_ALI_M5632 config USB_AN2720 bool "AnchorChips 2720 based cables (Xircom PGUNET, ...)" depends on USB_NET_CDC_SUBSET + select USB_NET_CDC_SUBSET_ENABLE help Choose this option if you're using a host-to-host cable based on this design. Note that AnchorChips is now a @@ -428,6 +434,7 @@ config USB_AN2720 config USB_BELKIN bool "eTEK based host-to-host cables (Advance, Belkin, ...)" depends on USB_NET_CDC_SUBSET + select USB_NET_CDC_SUBSET_ENABLE default y help Choose this option if you're using a host-to-host cable @@ -437,6 +444,7 @@ config USB_BELKIN config USB_ARMLINUX bool "Embedded ARM Linux links (iPaq, ...)" depends on USB_NET_CDC_SUBSET + select USB_NET_CDC_SUBSET_ENABLE default y help Choose this option to support the "usb-eth" networking driver @@ -454,6 +462,7 @@ config USB_ARMLINUX config USB_EPSON2888 bool "Epson 2888 based firmware (DEVELOPMENT)" depends on USB_NET_CDC_SUBSET + select USB_NET_CDC_SUBSET_ENABLE help Choose this option to support the usb networking links used by some sample firmware from Epson. @@ -461,6 +470,7 @@ config USB_EPSON2888 config USB_KC2190 bool "KT Technology KC2190 based cables (InstaNet)" depends on USB_NET_CDC_SUBSET + select USB_NET_CDC_SUBSET_ENABLE help Choose this option if you're using a host-to-host cable with one of these chips. diff --git a/drivers/net/usb/Makefile b/drivers/net/usb/Makefile index b5f04068dbe4..37fb46aee341 100644 --- a/drivers/net/usb/Makefile +++ b/drivers/net/usb/Makefile @@ -23,7 +23,7 @@ obj-$(CONFIG_USB_NET_GL620A) += gl620a.o obj-$(CONFIG_USB_NET_NET1080) += net1080.o obj-$(CONFIG_USB_NET_PLUSB) += plusb.o obj-$(CONFIG_USB_NET_RNDIS_HOST) += rndis_host.o -obj-$(CONFIG_USB_NET_CDC_SUBSET) += cdc_subset.o +obj-$(CONFIG_USB_NET_CDC_SUBSET_ENABLE) += cdc_subset.o obj-$(CONFIG_USB_NET_ZAURUS) += zaurus.o obj-$(CONFIG_USB_NET_MCS7830) += mcs7830.o obj-$(CONFIG_USB_USBNET) += usbnet.o From 69a8ec2d8155b9121ca2990d43f8363b8e2bf550 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 17 Feb 2016 13:11:12 -0800 Subject: [PATCH 312/489] thp, dax: do not try to withdraw pgtable from non-anon VMA DAX doesn't deposit pgtables when it maps huge pages: nothing to withdraw. It can lead to crash. Signed-off-by: Kirill A. Shutemov Cc: Dan Williams Cc: Matthew Wilcox Cc: Andrea Arcangeli Cc: Ross Zwisler Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 08fc0ba2207e..722546dcfb7e 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1700,7 +1700,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); - if (pmd_move_must_withdraw(new_ptl, old_ptl)) { + if (pmd_move_must_withdraw(new_ptl, old_ptl) && + vma_is_anonymous(vma)) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); pgtable_trans_huge_deposit(mm, new_pmd, pgtable); From 48f7df329474b49d83d0dffec1b6186647f11976 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 17 Feb 2016 13:11:15 -0800 Subject: [PATCH 313/489] mm: fix regression in remap_file_pages() emulation Grazvydas Ignotas has reported a regression in remap_file_pages() emulation. Testcase: #define _GNU_SOURCE #include #include #include #include #define SIZE (4096 * 3) int main(int argc, char **argv) { unsigned long *p; long i; p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); if (p == MAP_FAILED) { perror("mmap"); return -1; } for (i = 0; i < SIZE / 4096; i++) p[i * 4096 / sizeof(*p)] = i; if (remap_file_pages(p, 4096, 0, 1, 0)) { perror("remap_file_pages"); return -1; } if (remap_file_pages(p, 4096 * 2, 0, 1, 0)) { perror("remap_file_pages"); return -1; } assert(p[0] == 1); munmap(p, SIZE); return 0; } The second remap_file_pages() fails with -EINVAL. The reason is that remap_file_pages() emulation assumes that the target vma covers whole area we want to over map. That assumption is broken by first remap_file_pages() call: it split the area into two vma. The solution is to check next adjacent vmas, if they map the same file with the same flags. Fixes: c8d78c1823f4 ("mm: replace remap_file_pages() syscall with emulation") Signed-off-by: Kirill A. Shutemov Reported-by: Grazvydas Ignotas Tested-by: Grazvydas Ignotas Cc: [4.0+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 2f2415a7a688..76d1ec29149b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2664,12 +2664,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (start < vma->vm_start || start + size > vma->vm_end) + if (start < vma->vm_start) goto out; - if (pgoff == linear_page_index(vma, start)) { - ret = 0; - goto out; + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; @@ -2679,9 +2696,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ - munlock_vma_pages_range(vma, start, start + size); + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } } file = get_file(vma->vm_file); From 13d34ac6e55b8284c592c67e166ac614b3c4c1d7 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 17 Feb 2016 13:11:18 -0800 Subject: [PATCH 314/489] Revert "fsnotify: destroy marks with call_srcu instead of dedicated thread" This reverts commit c510eff6beba ("fsnotify: destroy marks with call_srcu instead of dedicated thread"). Eryu reported that he was seeing some OOM kills kick in when running a testcase that adds and removes inotify marks on a file in a tight loop. The above commit changed the code to use call_srcu to clean up the marks. While that does (in principle) work, the srcu callback job is limited to cleaning up entries in small batches and only once per jiffy. It's easily possible to overwhelm that machinery with too many call_srcu callbacks, and Eryu's reproduer did just that. There's also another potential problem with using call_srcu here. While you can obviously sleep while holding the srcu_read_lock, the callbacks run under local_bh_disable, so you can't sleep there. It's possible when putting the last reference to the fsnotify_mark that we'll end up putting a chain of references including the fsnotify_group, uid, and associated keys. While I don't see any obvious ways that that could occurs, it's probably still best to avoid using call_srcu here after all. This patch reverts the above patch. A later patch will take a different approach to eliminated the dedicated thread here. Signed-off-by: Jeff Layton Reported-by: Eryu Guan Tested-by: Eryu Guan Cc: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/mark.c | 66 +++++++++++++++++++++++++------- include/linux/fsnotify_backend.h | 5 +-- 2 files changed, 53 insertions(+), 18 deletions(-) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index cfcbf114676e..fc0df4442f7b 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -92,6 +92,9 @@ #include "fsnotify.h" struct srcu_struct fsnotify_mark_srcu; +static DEFINE_SPINLOCK(destroy_lock); +static LIST_HEAD(destroy_list); +static DECLARE_WAIT_QUEUE_HEAD(destroy_waitq); void fsnotify_get_mark(struct fsnotify_mark *mark) { @@ -165,19 +168,10 @@ void fsnotify_detach_mark(struct fsnotify_mark *mark) atomic_dec(&group->num_marks); } -static void -fsnotify_mark_free_rcu(struct rcu_head *rcu) -{ - struct fsnotify_mark *mark; - - mark = container_of(rcu, struct fsnotify_mark, g_rcu); - fsnotify_put_mark(mark); -} - /* - * Free fsnotify mark. The freeing is actually happening from a call_srcu - * callback. Caller must have a reference to the mark or be protected by - * fsnotify_mark_srcu. + * Free fsnotify mark. The freeing is actually happening from a kthread which + * first waits for srcu period end. Caller must have a reference to the mark + * or be protected by fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { @@ -192,7 +186,10 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); - call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); + spin_lock(&destroy_lock); + list_add(&mark->g_list, &destroy_list); + spin_unlock(&destroy_lock); + wake_up(&destroy_waitq); /* * Some groups like to know that marks are being freed. This is a @@ -388,7 +385,11 @@ err: spin_unlock(&mark->lock); - call_srcu(&fsnotify_mark_srcu, &mark->g_rcu, fsnotify_mark_free_rcu); + spin_lock(&destroy_lock); + list_add(&mark->g_list, &destroy_list); + spin_unlock(&destroy_lock); + wake_up(&destroy_waitq); + return ret; } @@ -491,3 +492,40 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, atomic_set(&mark->refcnt, 1); mark->free_mark = free_mark; } + +static int fsnotify_mark_destroy(void *ignored) +{ + struct fsnotify_mark *mark, *next; + struct list_head private_destroy_list; + + for (;;) { + spin_lock(&destroy_lock); + /* exchange the list head */ + list_replace_init(&destroy_list, &private_destroy_list); + spin_unlock(&destroy_lock); + + synchronize_srcu(&fsnotify_mark_srcu); + + list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { + list_del_init(&mark->g_list); + fsnotify_put_mark(mark); + } + + wait_event_interruptible(destroy_waitq, !list_empty(&destroy_list)); + } + + return 0; +} + +static int __init fsnotify_mark_init(void) +{ + struct task_struct *thread; + + thread = kthread_run(fsnotify_mark_destroy, NULL, + "fsnotify_mark"); + if (IS_ERR(thread)) + panic("unable to start fsnotify mark destruction thread."); + + return 0; +} +device_initcall(fsnotify_mark_init); diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index 6b7e89f45aa4..533c4408529a 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -220,10 +220,7 @@ struct fsnotify_mark { /* List of marks by group->i_fsnotify_marks. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ - union { - struct list_head g_list; - struct rcu_head g_rcu; - }; + struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [obj_lock] */ From 0918f1c309b86301605650c836ddd2021d311ae2 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Wed, 17 Feb 2016 13:11:21 -0800 Subject: [PATCH 315/489] fsnotify: turn fsnotify reaper thread into a workqueue job We don't require a dedicated thread for fsnotify cleanup. Switch it over to a workqueue job instead that runs on the system_unbound_wq. In the interest of not thrashing the queued job too often when there are a lot of marks being removed, we delay the reaper job slightly when queueing it, to allow several to gather on the list. Signed-off-by: Jeff Layton Tested-by: Eryu Guan Reviewed-by: Jan Kara Cc: Eric Paris Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/notify/mark.c | 49 ++++++++++++++++++------------------------------ 1 file changed, 18 insertions(+), 31 deletions(-) diff --git a/fs/notify/mark.c b/fs/notify/mark.c index fc0df4442f7b..7115c5d7d373 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -91,10 +91,14 @@ #include #include "fsnotify.h" +#define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ + struct srcu_struct fsnotify_mark_srcu; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); -static DECLARE_WAIT_QUEUE_HEAD(destroy_waitq); + +static void fsnotify_mark_destroy(struct work_struct *work); +static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy); void fsnotify_get_mark(struct fsnotify_mark *mark) { @@ -189,7 +193,8 @@ void fsnotify_free_mark(struct fsnotify_mark *mark) spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); - wake_up(&destroy_waitq); + queue_delayed_work(system_unbound_wq, &reaper_work, + FSNOTIFY_REAPER_DELAY); /* * Some groups like to know that marks are being freed. This is a @@ -388,7 +393,8 @@ err: spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); - wake_up(&destroy_waitq); + queue_delayed_work(system_unbound_wq, &reaper_work, + FSNOTIFY_REAPER_DELAY); return ret; } @@ -493,39 +499,20 @@ void fsnotify_init_mark(struct fsnotify_mark *mark, mark->free_mark = free_mark; } -static int fsnotify_mark_destroy(void *ignored) +static void fsnotify_mark_destroy(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; - for (;;) { - spin_lock(&destroy_lock); - /* exchange the list head */ - list_replace_init(&destroy_list, &private_destroy_list); - spin_unlock(&destroy_lock); + spin_lock(&destroy_lock); + /* exchange the list head */ + list_replace_init(&destroy_list, &private_destroy_list); + spin_unlock(&destroy_lock); - synchronize_srcu(&fsnotify_mark_srcu); + synchronize_srcu(&fsnotify_mark_srcu); - list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { - list_del_init(&mark->g_list); - fsnotify_put_mark(mark); - } - - wait_event_interruptible(destroy_waitq, !list_empty(&destroy_list)); + list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { + list_del_init(&mark->g_list); + fsnotify_put_mark(mark); } - - return 0; } - -static int __init fsnotify_mark_init(void) -{ - struct task_struct *thread; - - thread = kthread_run(fsnotify_mark_destroy, NULL, - "fsnotify_mark"); - if (IS_ERR(thread)) - panic("unable to start fsnotify mark destruction thread."); - - return 0; -} -device_initcall(fsnotify_mark_init); From 457a98b0809fa6cde7aab8c314a59d99772b445e Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Wed, 17 Feb 2016 13:11:23 -0800 Subject: [PATCH 316/489] mm, x86: fix pte_page() crash in gup_pte_range() Commit 3565fce3a659 ("mm, x86: get_user_pages() for dax mappings") has moved up the pte_page(pte) in x86's fast gup_pte_range(), for no discernible reason: put it back where it belongs, after the pte_flags check and the pfn_valid cross-check. That may be the cause of the NULL pointer dereference in gup_pte_range(), seen when vfio called vaddr_get_pfn() when starting a qemu-kvm based VM. Signed-off-by: Hugh Dickins Reported-by: Michael Long Tested-by: Michael Long Acked-by: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/mm/gup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c index 6d5eb5900372..d8a798d8bf50 100644 --- a/arch/x86/mm/gup.c +++ b/arch/x86/mm/gup.c @@ -102,7 +102,6 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } - page = pte_page(pte); if (pte_devmap(pte)) { pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { @@ -115,6 +114,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr, return 0; } VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + page = pte_page(pte); get_page(page); put_dev_pagemap(pgmap); SetPageReferenced(page); From f8b74815a452ff2904b5d7fcce1a5ae2a4d7ca5e Mon Sep 17 00:00:00 2001 From: Vaishali Thakkar Date: Wed, 17 Feb 2016 13:11:26 -0800 Subject: [PATCH 317/489] mm/hugetlb.c: fix incorrect proc nr_hugepages value Currently incorrect default hugepage pool size is reported by proc nr_hugepages when number of pages for the default huge page size is specified twice. When multiple huge page sizes are supported, /proc/sys/vm/nr_hugepages indicates the current number of pre-allocated huge pages of the default size. Basically /proc/sys/vm/nr_hugepages displays default_hstate-> max_huge_pages and after boot time pre-allocation, max_huge_pages should equal the number of pre-allocated pages (nr_hugepages). Test case: Note that this is specific to x86 architecture. Boot the kernel with command line option 'default_hugepagesz=1G hugepages=X hugepagesz=2M hugepages=Y hugepagesz=1G hugepages=Z'. After boot, 'cat /proc/sys/vm/nr_hugepages' and 'sysctl -a | grep hugepages' returns the value X. However, dmesg output shows that Z huge pages were pre-allocated. So, the root cause of the problem here is that the global variable default_hstate_max_huge_pages is set if a default huge page size is specified (directly or indirectly) on the command line. After the command line processing in hugetlb_init, if default_hstate_max_huge_pages is set, the value is assigned to default_hstae.max_huge_pages. However, default_hstate.max_huge_pages may have already been set based on the number of pre-allocated huge pages of default_hstate size. The solution to this problem is if hstate->max_huge_pages is already set then it should not set as a result of global max_huge_pages value. Basically if the value of the variable hugepages is set multiple times on a command line for a specific supported hugepagesize then proc layer should consider the last specified value. Signed-off-by: Vaishali Thakkar Reviewed-by: Naoya Horiguchi Cc: Mike Kravetz Cc: Hillf Danton Cc: Kirill A. Shutemov Cc: Dave Hansen Cc: Paul Gortmaker Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 06ae13e869d0..01f2b48c8618 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2630,8 +2630,10 @@ static int __init hugetlb_init(void) hugetlb_add_hstate(HUGETLB_PAGE_ORDER); } default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size)); - if (default_hstate_max_huge_pages) - default_hstate.max_huge_pages = default_hstate_max_huge_pages; + if (default_hstate_max_huge_pages) { + if (!default_hstate.max_huge_pages) + default_hstate.max_huge_pages = default_hstate_max_huge_pages; + } hugetlb_init_hstates(); gather_bootmem_prealloc(); From 9273a8bbf58a15051e53a777389a502420ddc60e Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Wed, 17 Feb 2016 13:11:29 -0800 Subject: [PATCH 318/489] devm_memremap_release(): fix memremap'd addr handling The pmem driver calls devm_memremap() to map a persistent memory range. When the pmem driver is unloaded, this memremap'd range is not released so the kernel will leak a vma. Fix devm_memremap_release() to handle a given memremap'd address properly. Signed-off-by: Toshi Kani Acked-by: Dan Williams Cc: Christoph Hellwig Cc: Ross Zwisler Cc: Matthew Wilcox Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/memremap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/memremap.c b/kernel/memremap.c index 2c468dea60bc..7a1b5c3ef14e 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(memunmap); static void devm_memremap_release(struct device *dev, void *res) { - memunmap(res); + memunmap(*(void **)res); } static int devm_memremap_match(struct device *dev, void *res, void *match_data) From 64f00850011b834746bab94119d1d5eb7eabb19a Mon Sep 17 00:00:00 2001 From: Shuah Khan Date: Wed, 17 Feb 2016 13:11:32 -0800 Subject: [PATCH 319/489] MAINTAINERS: update Kselftest Framework mailing list Kselftest Framework now has a dedicated mailing list linux-kselftest. Update the entry in MAINTAINERS file. Signed-off-by: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 28eb61bbecf4..4978dc19a4d2 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6128,7 +6128,7 @@ F: include/uapi/linux/sunrpc/ KERNEL SELFTEST FRAMEWORK M: Shuah Khan -L: linux-api@vger.kernel.org +L: linux-kselftest@vger.kernel.org T: git git://git.kernel.org/pub/scm/shuah/linux-kselftest S: Maintained F: tools/testing/selftests From 1ac0b6dec656f3f78d1c3dd216fad84cb4d0a01e Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 17 Feb 2016 13:11:35 -0800 Subject: [PATCH 320/489] ipc/shm: handle removed segments gracefully in shm_mmap() remap_file_pages(2) emulation can reach file which represents removed IPC ID as long as a memory segment is mapped. It breaks expectations of IPC subsystem. Test case (rewritten to be more human readable, originally autogenerated by syzkaller[1]): #define _GNU_SOURCE #include #include #include #include #define PAGE_SIZE 4096 int main() { int id; void *p; id = shmget(IPC_PRIVATE, 3 * PAGE_SIZE, 0); p = shmat(id, NULL, 0); shmctl(id, IPC_RMID, NULL); remap_file_pages(p, 3 * PAGE_SIZE, 0, 7, 0); return 0; } The patch changes shm_mmap() and code around shm_lock() to propagate locking error back to caller of shm_mmap(). [1] http://github.com/google/syzkaller Signed-off-by: Kirill A. Shutemov Reported-by: Dmitry Vyukov Cc: Davidlohr Bueso Cc: Manfred Spraul Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/shm.c | 55 ++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 44 insertions(+), 11 deletions(-) diff --git a/ipc/shm.c b/ipc/shm.c index ed3027d0f277..331fc1b0b3c7 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -156,11 +156,12 @@ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id); /* - * We raced in the idr lookup or with shm_destroy(). Either way, the - * ID is busted. + * Callers of shm_lock() must validate the status of the returned ipc + * object pointer (as returned by ipc_lock()), and error out as + * appropriate. */ - WARN_ON(IS_ERR(ipcp)); - + if (IS_ERR(ipcp)) + return (void *)ipcp; return container_of(ipcp, struct shmid_kernel, shm_perm); } @@ -186,18 +187,33 @@ static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s) } -/* This is called by fork, once for every shm attach. */ -static void shm_open(struct vm_area_struct *vma) +static int __shm_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct shm_file_data *sfd = shm_file_data(file); struct shmid_kernel *shp; shp = shm_lock(sfd->ns, sfd->id); + + if (IS_ERR(shp)) + return PTR_ERR(shp); + shp->shm_atim = get_seconds(); shp->shm_lprid = task_tgid_vnr(current); shp->shm_nattch++; shm_unlock(shp); + return 0; +} + +/* This is called by fork, once for every shm attach. */ +static void shm_open(struct vm_area_struct *vma) +{ + int err = __shm_open(vma); + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + WARN_ON_ONCE(err); } /* @@ -260,6 +276,14 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rwsem); /* remove from the list of attaches of the shm segment */ shp = shm_lock(ns, sfd->id); + + /* + * We raced in the idr lookup or with shm_destroy(). + * Either way, the ID is busted. + */ + if (WARN_ON_ONCE(IS_ERR(shp))) + goto done; /* no-op */ + shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); shp->shm_nattch--; @@ -267,6 +291,7 @@ static void shm_close(struct vm_area_struct *vma) shm_destroy(ns, shp); else shm_unlock(shp); +done: up_write(&shm_ids(ns).rwsem); } @@ -388,17 +413,25 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma) struct shm_file_data *sfd = shm_file_data(file); int ret; - ret = sfd->file->f_op->mmap(sfd->file, vma); - if (ret != 0) + /* + * In case of remap_file_pages() emulation, the file can represent + * removed IPC ID: propogate shm_lock() error to caller. + */ + ret =__shm_open(vma); + if (ret) return ret; + + ret = sfd->file->f_op->mmap(sfd->file, vma); + if (ret) { + shm_close(vma); + return ret; + } sfd->vm_ops = vma->vm_ops; #ifdef CONFIG_MMU WARN_ON(!sfd->vm_ops->fault); #endif vma->vm_ops = &shm_vm_ops; - shm_open(vma); - - return ret; + return 0; } static int shm_release(struct inode *ino, struct file *file) From 52b4b950b50740bff507a62907e86710743c22e7 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Wed, 17 Feb 2016 13:11:37 -0800 Subject: [PATCH 321/489] mm: slab: free kmem_cache_node after destroy sysfs file When slub_debug alloc_calls_show is enabled we will try to track location and user of slab object on each online node, kmem_cache_node structure and cpu_cache/cpu_slub shouldn't be freed till there is the last reference to sysfs file. This fixes the following panic: BUG: unable to handle kernel NULL pointer dereference at 0000000000000020 IP: list_locations+0x169/0x4e0 PGD 257304067 PUD 438456067 PMD 0 Oops: 0000 [#1] SMP CPU: 3 PID: 973074 Comm: cat ve: 0 Not tainted 3.10.0-229.7.2.ovz.9.30-00007-japdoll-dirty #2 9.30 Hardware name: DEPO Computers To Be Filled By O.E.M./H67DE3, BIOS L1.60c 07/14/2011 task: ffff88042a5dc5b0 ti: ffff88037f8d8000 task.ti: ffff88037f8d8000 RIP: list_locations+0x169/0x4e0 Call Trace: alloc_calls_show+0x1d/0x30 slab_attr_show+0x1b/0x30 sysfs_read_file+0x9a/0x1a0 vfs_read+0x9c/0x170 SyS_read+0x58/0xb0 system_call_fastpath+0x16/0x1b Code: 5e 07 12 00 b9 00 04 00 00 3d 00 04 00 00 0f 4f c1 3d 00 04 00 00 89 45 b0 0f 84 c3 00 00 00 48 63 45 b0 49 8b 9c c4 f8 00 00 00 <48> 8b 43 20 48 85 c0 74 b6 48 89 df e8 46 37 44 00 48 8b 53 10 CR2: 0000000000000020 Separated __kmem_cache_release from __kmem_cache_shutdown which now called on slab_kmem_cache_release (after the last reference to sysfs file object has dropped). Reintroduced locking in free_partial as sysfs file might access cache's partial list after shutdowning - partial revert of the commit 69cb8e6b7c29 ("slub: free slabs without holding locks"). Zap __remove_partial and use remove_partial (w/o underscores) as free_partial now takes list_lock which s partial revert for commit 1e4dd9461fab ("slub: do not assert not having lock in removing freed partial") Signed-off-by: Dmitry Safonov Suggested-by: Vladimir Davydov Acked-by: Vladimir Davydov Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 12 ++++++------ mm/slab.h | 1 + mm/slab_common.c | 1 + mm/slob.c | 4 ++++ mm/slub.c | 38 +++++++++++++++++--------------------- 5 files changed, 29 insertions(+), 27 deletions(-) diff --git a/mm/slab.c b/mm/slab.c index 6ecc697a8bc4..621fbcb35a36 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2275,7 +2275,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) err = setup_cpu_cache(cachep, gfp); if (err) { - __kmem_cache_shutdown(cachep); + __kmem_cache_release(cachep); return err; } @@ -2413,13 +2413,14 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate) } int __kmem_cache_shutdown(struct kmem_cache *cachep) +{ + return __kmem_cache_shrink(cachep, false); +} + +void __kmem_cache_release(struct kmem_cache *cachep) { int i; struct kmem_cache_node *n; - int rc = __kmem_cache_shrink(cachep, false); - - if (rc) - return rc; free_percpu(cachep->cpu_cache); @@ -2430,7 +2431,6 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep) kfree(n); cachep->node[i] = NULL; } - return 0; } /* diff --git a/mm/slab.h b/mm/slab.h index 834ad240c0bb..2eedacea439d 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -140,6 +140,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) int __kmem_cache_shutdown(struct kmem_cache *); +void __kmem_cache_release(struct kmem_cache *); int __kmem_cache_shrink(struct kmem_cache *, bool); void slab_kmem_cache_release(struct kmem_cache *); diff --git a/mm/slab_common.c b/mm/slab_common.c index b50aef01ccf7..065b7bdabdc3 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -693,6 +693,7 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s, void slab_kmem_cache_release(struct kmem_cache *s) { + __kmem_cache_release(s); destroy_memcg_params(s); kfree_const(s->name); kmem_cache_free(kmem_cache, s); diff --git a/mm/slob.c b/mm/slob.c index 17e8f8cc7c53..5ec158054ffe 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -630,6 +630,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c) return 0; } +void __kmem_cache_release(struct kmem_cache *c) +{ +} + int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate) { return 0; diff --git a/mm/slub.c b/mm/slub.c index 2e1355ac056b..d8fbd4a6ed59 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1592,18 +1592,12 @@ static inline void add_partial(struct kmem_cache_node *n, __add_partial(n, page, tail); } -static inline void -__remove_partial(struct kmem_cache_node *n, struct page *page) -{ - list_del(&page->lru); - n->nr_partial--; -} - static inline void remove_partial(struct kmem_cache_node *n, struct page *page) { lockdep_assert_held(&n->list_lock); - __remove_partial(n, page); + list_del(&page->lru); + n->nr_partial--; } /* @@ -3184,6 +3178,12 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) } } +void __kmem_cache_release(struct kmem_cache *s) +{ + free_percpu(s->cpu_slab); + free_kmem_cache_nodes(s); +} + static int init_kmem_cache_nodes(struct kmem_cache *s) { int node; @@ -3443,28 +3443,31 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, /* * Attempt to free all partial slabs on a node. - * This is called from kmem_cache_close(). We must be the last thread - * using the cache and therefore we do not need to lock anymore. + * This is called from __kmem_cache_shutdown(). We must take list_lock + * because sysfs file might still access partial list after the shutdowning. */ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { struct page *page, *h; + BUG_ON(irqs_disabled()); + spin_lock_irq(&n->list_lock); list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - __remove_partial(n, page); + remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, - "Objects remaining in %s on kmem_cache_close()"); + "Objects remaining in %s on __kmem_cache_shutdown()"); } } + spin_unlock_irq(&n->list_lock); } /* * Release all resources used by a slab cache. */ -static inline int kmem_cache_close(struct kmem_cache *s) +int __kmem_cache_shutdown(struct kmem_cache *s) { int node; struct kmem_cache_node *n; @@ -3476,16 +3479,9 @@ static inline int kmem_cache_close(struct kmem_cache *s) if (n->nr_partial || slabs_node(s, node)) return 1; } - free_percpu(s->cpu_slab); - free_kmem_cache_nodes(s); return 0; } -int __kmem_cache_shutdown(struct kmem_cache *s) -{ - return kmem_cache_close(s); -} - /******************************************************************** * Kmalloc subsystem *******************************************************************/ @@ -3980,7 +3976,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags) memcg_propagate_slab_attrs(s); err = sysfs_slab_add(s); if (err) - kmem_cache_close(s); + __kmem_cache_release(s); return err; } From 4462b4bbfc33a44f19710ead784ff361bda2c3b3 Mon Sep 17 00:00:00 2001 From: Stephen Boyd Date: Thu, 18 Feb 2016 19:07:44 -0800 Subject: [PATCH 322/489] clk: gpio: Really allow an optional clock= DT property We mis-merged the original patch from Russell here and so the patch went almost all the way, except that we still failed to probe when there wasn't a clocks property in the DT node. Allow that case by making a negative value from of_clk_get_parent_count() into "no parents", like the original patch did. Fixes: 7ed88aa2efa5 ("clk: fix clk-gpio.c with optional clock= DT property") Cc: Russell King Cc: Michael Turquette Signed-off-by: Stephen Boyd --- drivers/clk/clk-gpio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/clk/clk-gpio.c b/drivers/clk/clk-gpio.c index 19fed65587e8..7b09a265d79f 100644 --- a/drivers/clk/clk-gpio.c +++ b/drivers/clk/clk-gpio.c @@ -289,7 +289,7 @@ static void __init of_gpio_clk_setup(struct device_node *node, num_parents = of_clk_get_parent_count(node); if (num_parents < 0) - return; + num_parents = 0; data = kzalloc(sizeof(*data), GFP_KERNEL); if (!data) From acc146943957d7418a6846f06e029b2c5e87e0d5 Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Thu, 18 Feb 2016 14:07:52 +0100 Subject: [PATCH 323/489] hwmon: (ads1015) Handle negative conversion values correctly Make the divisor signed as DIV_ROUND_CLOSEST is undefined for negative dividends when the divisor is unsigned. Signed-off-by: Peter Rosin Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck --- drivers/hwmon/ads1015.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/hwmon/ads1015.c b/drivers/hwmon/ads1015.c index f155b8380481..2b3105c8aed3 100644 --- a/drivers/hwmon/ads1015.c +++ b/drivers/hwmon/ads1015.c @@ -126,7 +126,7 @@ static int ads1015_reg_to_mv(struct i2c_client *client, unsigned int channel, struct ads1015_data *data = i2c_get_clientdata(client); unsigned int pga = data->channel_data[channel].pga; int fullscale = fullscale_table[pga]; - const unsigned mask = data->id == ads1115 ? 0x7fff : 0x7ff0; + const int mask = data->id == ads1115 ? 0x7fff : 0x7ff0; return DIV_ROUND_CLOSEST(reg * fullscale, mask); } From 5fff80bbdb6b84a94f90391ba674471d37b57eb2 Mon Sep 17 00:00:00 2001 From: Maarten Lankhorst Date: Wed, 17 Feb 2016 08:32:05 +0100 Subject: [PATCH 324/489] drm/atomic: Allow for holes in connector state, v2. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Because we record connector_mask using 1 << drm_connector_index now the connector_mask should stay the same even when other connectors are removed. This was not the case with MST, in that case when removing a connector all other connectors may change their index. This is fixed by waiting until the first get_connector_state to allocate connector_state, and force reallocation when state is too small. As a side effect connector arrays no longer have to be preallocated, and can be allocated on first use which means a less allocations in the page flip only path. Changes since v1: - Whitespace. (Ville) - Call ida_remove when destroying the connector. (Ville) - u32 alloc -> int. (Ville) Fixes: 14de6c44d149 ("drm/atomic: Remove drm_atomic_connectors_for_crtc.") Signed-off-by: Maarten Lankhorst Cc: Ville Syrjälä Reviewed-by: Lyude Reviewed-by: Ville Syrjälä Signed-off-by: Dave Airlie --- drivers/gpu/drm/drm_atomic.c | 44 ++++++++++++-------------- drivers/gpu/drm/drm_atomic_helper.c | 2 +- drivers/gpu/drm/drm_crtc.c | 49 ++++++++++++----------------- include/drm/drm_crtc.h | 8 ++++- 4 files changed, 48 insertions(+), 55 deletions(-) diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c index 3f74193885f1..9a7b44616b55 100644 --- a/drivers/gpu/drm/drm_atomic.c +++ b/drivers/gpu/drm/drm_atomic.c @@ -65,8 +65,6 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state) */ state->allow_modeset = true; - state->num_connector = ACCESS_ONCE(dev->mode_config.num_connector); - state->crtcs = kcalloc(dev->mode_config.num_crtc, sizeof(*state->crtcs), GFP_KERNEL); if (!state->crtcs) @@ -83,16 +81,6 @@ drm_atomic_state_init(struct drm_device *dev, struct drm_atomic_state *state) sizeof(*state->plane_states), GFP_KERNEL); if (!state->plane_states) goto fail; - state->connectors = kcalloc(state->num_connector, - sizeof(*state->connectors), - GFP_KERNEL); - if (!state->connectors) - goto fail; - state->connector_states = kcalloc(state->num_connector, - sizeof(*state->connector_states), - GFP_KERNEL); - if (!state->connector_states) - goto fail; state->dev = dev; @@ -823,19 +811,27 @@ drm_atomic_get_connector_state(struct drm_atomic_state *state, index = drm_connector_index(connector); - /* - * Construction of atomic state updates can race with a connector - * hot-add which might overflow. In this case flip the table and just - * restart the entire ioctl - no one is fast enough to livelock a cpu - * with physical hotplug events anyway. - * - * Note that we only grab the indexes once we have the right lock to - * prevent hotplug/unplugging of connectors. So removal is no problem, - * at most the array is a bit too large. - */ if (index >= state->num_connector) { - DRM_DEBUG_ATOMIC("Hot-added connector would overflow state array, restarting\n"); - return ERR_PTR(-EAGAIN); + struct drm_connector **c; + struct drm_connector_state **cs; + int alloc = max(index + 1, config->num_connector); + + c = krealloc(state->connectors, alloc * sizeof(*state->connectors), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + state->connectors = c; + memset(&state->connectors[state->num_connector], 0, + sizeof(*state->connectors) * (alloc - state->num_connector)); + + cs = krealloc(state->connector_states, alloc * sizeof(*state->connector_states), GFP_KERNEL); + if (!cs) + return ERR_PTR(-ENOMEM); + + state->connector_states = cs; + memset(&state->connector_states[state->num_connector], 0, + sizeof(*state->connector_states) * (alloc - state->num_connector)); + state->num_connector = alloc; } if (state->connector_states[index]) diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 7c523060a076..4f2d3e161593 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -1493,7 +1493,7 @@ void drm_atomic_helper_swap_state(struct drm_device *dev, { int i; - for (i = 0; i < dev->mode_config.num_connector; i++) { + for (i = 0; i < state->num_connector; i++) { struct drm_connector *connector = state->connectors[i]; if (!connector) diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index d40bab29747e..f6191215b2cb 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -918,12 +918,19 @@ int drm_connector_init(struct drm_device *dev, connector->base.properties = &connector->properties; connector->dev = dev; connector->funcs = funcs; + + connector->connector_id = ida_simple_get(&config->connector_ida, 0, 0, GFP_KERNEL); + if (connector->connector_id < 0) { + ret = connector->connector_id; + goto out_put; + } + connector->connector_type = connector_type; connector->connector_type_id = ida_simple_get(connector_ida, 1, 0, GFP_KERNEL); if (connector->connector_type_id < 0) { ret = connector->connector_type_id; - goto out_put; + goto out_put_id; } connector->name = kasprintf(GFP_KERNEL, "%s-%d", @@ -931,7 +938,7 @@ int drm_connector_init(struct drm_device *dev, connector->connector_type_id); if (!connector->name) { ret = -ENOMEM; - goto out_put; + goto out_put_type_id; } INIT_LIST_HEAD(&connector->probed_modes); @@ -959,7 +966,12 @@ int drm_connector_init(struct drm_device *dev, } connector->debugfs_entry = NULL; - +out_put_type_id: + if (ret) + ida_remove(connector_ida, connector->connector_type_id); +out_put_id: + if (ret) + ida_remove(&config->connector_ida, connector->connector_id); out_put: if (ret) drm_mode_object_put(dev, &connector->base); @@ -996,6 +1008,9 @@ void drm_connector_cleanup(struct drm_connector *connector) ida_remove(&drm_connector_enum_list[connector->connector_type].ida, connector->connector_type_id); + ida_remove(&dev->mode_config.connector_ida, + connector->connector_id); + kfree(connector->display_info.bus_formats); drm_mode_object_put(dev, &connector->base); kfree(connector->name); @@ -1012,32 +1027,6 @@ void drm_connector_cleanup(struct drm_connector *connector) } EXPORT_SYMBOL(drm_connector_cleanup); -/** - * drm_connector_index - find the index of a registered connector - * @connector: connector to find index for - * - * Given a registered connector, return the index of that connector within a DRM - * device's list of connectors. - */ -unsigned int drm_connector_index(struct drm_connector *connector) -{ - unsigned int index = 0; - struct drm_connector *tmp; - struct drm_mode_config *config = &connector->dev->mode_config; - - WARN_ON(!drm_modeset_is_locked(&config->connection_mutex)); - - drm_for_each_connector(tmp, connector->dev) { - if (tmp == connector) - return index; - - index++; - } - - BUG(); -} -EXPORT_SYMBOL(drm_connector_index); - /** * drm_connector_register - register a connector * @connector: the connector to register @@ -5789,6 +5778,7 @@ void drm_mode_config_init(struct drm_device *dev) INIT_LIST_HEAD(&dev->mode_config.plane_list); idr_init(&dev->mode_config.crtc_idr); idr_init(&dev->mode_config.tile_idr); + ida_init(&dev->mode_config.connector_ida); drm_modeset_lock_all(dev); drm_mode_create_standard_properties(dev); @@ -5869,6 +5859,7 @@ void drm_mode_config_cleanup(struct drm_device *dev) crtc->funcs->destroy(crtc); } + ida_destroy(&dev->mode_config.connector_ida); idr_destroy(&dev->mode_config.tile_idr); idr_destroy(&dev->mode_config.crtc_idr); drm_modeset_lock_fini(&dev->mode_config.connection_mutex); diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h index c65a212db77e..c5b4b81a831b 100644 --- a/include/drm/drm_crtc.h +++ b/include/drm/drm_crtc.h @@ -1166,6 +1166,7 @@ struct drm_connector { struct drm_mode_object base; char *name; + int connector_id; int connector_type; int connector_type_id; bool interlace_allowed; @@ -2047,6 +2048,7 @@ struct drm_mode_config { struct list_head fb_list; int num_connector; + struct ida connector_ida; struct list_head connector_list; int num_encoder; struct list_head encoder_list; @@ -2200,7 +2202,11 @@ int drm_connector_register(struct drm_connector *connector); void drm_connector_unregister(struct drm_connector *connector); extern void drm_connector_cleanup(struct drm_connector *connector); -extern unsigned int drm_connector_index(struct drm_connector *connector); +static inline unsigned drm_connector_index(struct drm_connector *connector) +{ + return connector->connector_id; +} + /* helper to unplug all connectors from sysfs for device */ extern void drm_connector_unplug_all(struct drm_device *dev); From 4fbbed46dca83bcba3a0170205110a06c116a8e6 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Mon, 15 Feb 2016 19:41:46 +0100 Subject: [PATCH 325/489] drm/nouveau: use post-decrement in error handling We need to use post-decrement to get the dma_map_page undone also for i==0, and to avoid some very unpleasant behaviour if dma_map_page failed already at i==0. Signed-off-by: Rasmus Villemoes Reviewed-by: Ben Skeggs Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_bo.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 78f520d05de9..e3acc35e3805 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -1520,7 +1520,7 @@ nouveau_ttm_tt_populate(struct ttm_tt *ttm) DMA_BIDIRECTIONAL); if (dma_mapping_error(pdev, addr)) { - while (--i) { + while (i--) { dma_unmap_page(pdev, ttm_dma->dma_address[i], PAGE_SIZE, DMA_BIDIRECTIONAL); ttm_dma->dma_address[i] = 0; From ed8ad83808f009ade97ebbf6519bc3a97fefbc0c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 19 Feb 2016 00:18:25 -0500 Subject: [PATCH 326/489] ext4: fix bh->b_state corruption ext4 can update bh->b_state non-atomically in _ext4_get_block() and ext4_da_get_block_prep(). Usually this is fine since bh is just a temporary storage for mapping information on stack but in some cases it can be fully living bh attached to a page. In such case non-atomic update of bh->b_state can race with an atomic update which then gets lost. Usually when we are mapping bh and thus updating bh->b_state non-atomically, nobody else touches the bh and so things work out fine but there is one case to especially worry about: ext4_finish_bio() uses BH_Uptodate_Lock on the first bh in the page to synchronize handling of PageWriteback state. So when blocksize < pagesize, we can be atomically modifying bh->b_state of a buffer that actually isn't under IO and thus can race e.g. with delalloc trying to map that buffer. The result is that we can mistakenly set / clear BH_Uptodate_Lock bit resulting in the corruption of PageWriteback state or missed unlock of BH_Uptodate_Lock. Fix the problem by always updating bh->b_state bits atomically. CC: stable@vger.kernel.org Reported-by: Nikolay Borisov Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 83bc8bfb3bea..d6674479269d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -686,6 +686,34 @@ out_sem: return retval; } +/* + * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages + * we have to be careful as someone else may be manipulating b_state as well. + */ +static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) +{ + unsigned long old_state; + unsigned long new_state; + + flags &= EXT4_MAP_FLAGS; + + /* Dummy buffer_head? Set non-atomically. */ + if (!bh->b_page) { + bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; + return; + } + /* + * Someone else may be modifying b_state. Be careful! This is ugly but + * once we get rid of using bh as a container for mapping information + * to pass to / from get_block functions, this can go away. + */ + do { + old_state = READ_ONCE(bh->b_state); + new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; + } while (unlikely( + cmpxchg(&bh->b_state, old_state, new_state) != old_state)); +} + /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 @@ -722,7 +750,7 @@ static int _ext4_get_block(struct inode *inode, sector_t iblock, ext4_io_end_t *io_end = ext4_inode_aio(inode); map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (io_end && io_end->flag & EXT4_IO_END_UNWRITTEN) set_buffer_defer_completion(bh); bh->b_size = inode->i_sb->s_blocksize * map.m_len; @@ -1685,7 +1713,7 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, return ret; map_bh(bh, inode->i_sb, map.m_pblk); - bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | map.m_flags; + ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked From 74dae4278546b897eb81784fdfcce872ddd8b2b8 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 19 Feb 2016 00:33:21 -0500 Subject: [PATCH 327/489] ext4: fix crashes in dioread_nolock mode Competing overwrite DIO in dioread_nolock mode will just overwrite pointer to io_end in the inode. This may result in data corruption or extent conversion happening from IO completion interrupt because we don't properly set buffer_defer_completion() when unlocked DIO races with locked DIO to unwritten extent. Since unlocked DIO doesn't need io_end for anything, just avoid allocating it and corrupting pointer from inode for locked DIO. A cleaner fix would be to avoid these games with io_end pointer from the inode but that requires more intrusive changes so we leave that for later. Cc: stable@vger.kernel.org Signed-off-by: Jan Kara Signed-off-by: Theodore Ts'o --- fs/ext4/inode.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d6674479269d..9cc57c3b4661 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3281,29 +3281,29 @@ static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter, * case, we allocate an io_end structure to hook to the iocb. */ iocb->private = NULL; - ext4_inode_aio_set(inode, NULL); - if (!is_sync_kiocb(iocb)) { - io_end = ext4_init_io_end(inode, GFP_NOFS); - if (!io_end) { - ret = -ENOMEM; - goto retake_lock; - } - /* - * Grab reference for DIO. Will be dropped in ext4_end_io_dio() - */ - iocb->private = ext4_get_io_end(io_end); - /* - * we save the io structure for current async direct - * IO, so that later ext4_map_blocks() could flag the - * io structure whether there is a unwritten extents - * needs to be converted when IO is completed. - */ - ext4_inode_aio_set(inode, io_end); - } - if (overwrite) { get_block_func = ext4_get_block_overwrite; } else { + ext4_inode_aio_set(inode, NULL); + if (!is_sync_kiocb(iocb)) { + io_end = ext4_init_io_end(inode, GFP_NOFS); + if (!io_end) { + ret = -ENOMEM; + goto retake_lock; + } + /* + * Grab reference for DIO. Will be dropped in + * ext4_end_io_dio() + */ + iocb->private = ext4_get_io_end(io_end); + /* + * we save the io structure for current async direct + * IO, so that later ext4_map_blocks() could flag the + * io structure whether there is a unwritten extents + * needs to be converted when IO is completed. + */ + ext4_inode_aio_set(inode, io_end); + } get_block_func = ext4_get_block_write; dio_flags = DIO_LOCKING; } From a4de018d2b0364e40a626fa521ec21e31a10ac84 Mon Sep 17 00:00:00 2001 From: Alan Date: Mon, 15 Feb 2016 19:09:46 +0000 Subject: [PATCH 328/489] usb: chipidea: error on overflow for port_test_write The write value is 8bit, but currently writing a larger number (eg a doubled digit) is not errored but instead gets cast and sets off an action probably undesired. Signed-off-by: Alan Cox Signed-off-by: Peter Chen (Change the style of commit log to fix checkpatch.pl warning) --- drivers/usb/chipidea/debug.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c index a4f7db2e18dd..df47110bad2d 100644 --- a/drivers/usb/chipidea/debug.c +++ b/drivers/usb/chipidea/debug.c @@ -100,6 +100,9 @@ static ssize_t ci_port_test_write(struct file *file, const char __user *ubuf, if (sscanf(buf, "%u", &mode) != 1) return -EINVAL; + if (mode > 255) + return -EBADRQC; + pm_runtime_get_sync(ci->dev); spin_lock_irqsave(&ci->lock, flags); ret = hw_port_test_set(ci, mode); From 8c0614ca312c847ca5409ea11c39434dec69631d Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sat, 6 Feb 2016 22:57:06 +0800 Subject: [PATCH 329/489] usb: chipidea: fix return value check in ci_hdrc_pci_probe() In case of error, the function usb_phy_generic_register() returns ERR_PTR() and never returns NULL. The NULL test in the return value check should be replaced with IS_ERR(). Signed-off-by: Wei Yongjun Signed-off-by: Peter Chen --- drivers/usb/chipidea/ci_hdrc_pci.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/usb/chipidea/ci_hdrc_pci.c b/drivers/usb/chipidea/ci_hdrc_pci.c index b59195edf636..b635ab67490d 100644 --- a/drivers/usb/chipidea/ci_hdrc_pci.c +++ b/drivers/usb/chipidea/ci_hdrc_pci.c @@ -85,8 +85,8 @@ static int ci_hdrc_pci_probe(struct pci_dev *pdev, /* register a nop PHY */ ci->phy = usb_phy_generic_register(); - if (!ci->phy) - return -ENOMEM; + if (IS_ERR(ci->phy)) + return PTR_ERR(ci->phy); memset(res, 0, sizeof(res)); res[0].start = pci_resource_start(pdev, 0); From 8684fa3e7a9ee629ca60bd811d1597646451f918 Mon Sep 17 00:00:00 2001 From: Masahiro Yamada Date: Fri, 19 Feb 2016 15:05:50 +0900 Subject: [PATCH 330/489] arm64: kbuild: make "make install" not depend on vmlinux For the same reason as commit 19514fc665ff ("arm, kbuild: make "make install" not depend on vmlinux"), the install targets should never trigger the rebuild of the kernel. Signed-off-by: Masahiro Yamada Signed-off-by: Will Deacon --- arch/arm64/Makefile | 2 +- arch/arm64/boot/Makefile | 4 ++-- arch/arm64/boot/install.sh | 14 ++++++++++++++ 3 files changed, 17 insertions(+), 3 deletions(-) diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 307237cfe728..b5e3f6d42b88 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -88,7 +88,7 @@ Image: vmlinux Image.%: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ -zinstall install: vmlinux +zinstall install: $(Q)$(MAKE) $(build)=$(boot) $@ %.dtb: scripts diff --git a/arch/arm64/boot/Makefile b/arch/arm64/boot/Makefile index abcbba2f01ba..305c552b5ec1 100644 --- a/arch/arm64/boot/Makefile +++ b/arch/arm64/boot/Makefile @@ -34,10 +34,10 @@ $(obj)/Image.lzma: $(obj)/Image FORCE $(obj)/Image.lzo: $(obj)/Image FORCE $(call if_changed,lzo) -install: $(obj)/Image +install: $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \ $(obj)/Image System.map "$(INSTALL_PATH)" -zinstall: $(obj)/Image.gz +zinstall: $(CONFIG_SHELL) $(srctree)/$(src)/install.sh $(KERNELRELEASE) \ $(obj)/Image.gz System.map "$(INSTALL_PATH)" diff --git a/arch/arm64/boot/install.sh b/arch/arm64/boot/install.sh index 12ed78aa6f0c..d91e1f022573 100644 --- a/arch/arm64/boot/install.sh +++ b/arch/arm64/boot/install.sh @@ -20,6 +20,20 @@ # $4 - default install path (blank if root directory) # +verify () { + if [ ! -f "$1" ]; then + echo "" 1>&2 + echo " *** Missing file: $1" 1>&2 + echo ' *** You need to run "make" before "make install".' 1>&2 + echo "" 1>&2 + exit 1 + fi +} + +# Make sure the files actually exist +verify "$2" +verify "$3" + # User may have a custom install script if [ -x ~/bin/${INSTALLKERNEL} ]; then exec ~/bin/${INSTALLKERNEL} "$@"; fi if [ -x /sbin/${INSTALLKERNEL} ]; then exec /sbin/${INSTALLKERNEL} "$@"; fi From 52d7523d84d534c241ebac5ac89f5c0a6cb51e41 Mon Sep 17 00:00:00 2001 From: EunTaik Lee Date: Tue, 16 Feb 2016 04:44:35 +0000 Subject: [PATCH 331/489] arm64: mm: allow the kernel to handle alignment faults on user accesses Although we don't expect to take alignment faults on access to normal memory, misbehaving (i.e. buggy) user code can pass MMIO pointers into system calls, leading to things like get_user accessing device memory. Rather than OOPS the kernel, allow any exception fixups to run and return something like -EFAULT back to userspace. This makes the behaviour more consistent with userspace, even though applications with access to device mappings can easily cause other issues if they try hard enough. Acked-by: Catalin Marinas Signed-off-by: Eun Taik Lee [will: dropped __kprobes annotation and rewrote commit mesage] Signed-off-by: Will Deacon --- arch/arm64/mm/fault.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 92ddac1e8ca2..abe2a9542b3a 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -371,6 +371,13 @@ static int __kprobes do_translation_fault(unsigned long addr, return 0; } +static int do_alignment_fault(unsigned long addr, unsigned int esr, + struct pt_regs *regs) +{ + do_bad_area(addr, esr, regs); + return 0; +} + /* * This abort handler always returns "fault". */ @@ -418,7 +425,7 @@ static struct fault_info { { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, { do_bad, SIGBUS, 0, "synchronous parity error (translation table walk)" }, { do_bad, SIGBUS, 0, "unknown 32" }, - { do_bad, SIGBUS, BUS_ADRALN, "alignment fault" }, + { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" }, { do_bad, SIGBUS, 0, "unknown 34" }, { do_bad, SIGBUS, 0, "unknown 35" }, { do_bad, SIGBUS, 0, "unknown 36" }, From e327b3f564031a8d0090a6b3e3562a8b59bafe0e Mon Sep 17 00:00:00 2001 From: Peter Ujfalusi Date: Fri, 19 Feb 2016 16:12:19 +0200 Subject: [PATCH 332/489] Revert "regulator: tps65217: remove tps65217.dtsi file" This reverts commit 8e6ebfaa9b384088002baa10f7534efa73a0794e. Without the patch reverted regulators will not work. This prevents MMC to be working for example so the boards can not boot to MMC rootfs. Tested it on beaglebone white and bisect also points to the reverted commit. The issue can be also fixed by adding "regulator-compatible =" to all board dts file for the regulators. Signed-off-by: Peter Ujfalusi Signed-off-by: Tony Lindgren --- .../bindings/regulator/tps65217.txt | 10 ---- arch/arm/boot/dts/am335x-bone-common.dtsi | 14 +---- arch/arm/boot/dts/am335x-chilisom.dtsi | 14 +---- arch/arm/boot/dts/am335x-nano.dts | 14 +---- arch/arm/boot/dts/am335x-pepper.dts | 14 +---- arch/arm/boot/dts/am335x-sl50.dts | 13 +---- arch/arm/boot/dts/tps65217.dtsi | 56 +++++++++++++++++++ 7 files changed, 67 insertions(+), 68 deletions(-) create mode 100644 arch/arm/boot/dts/tps65217.dtsi diff --git a/Documentation/devicetree/bindings/regulator/tps65217.txt b/Documentation/devicetree/bindings/regulator/tps65217.txt index d18109657da6..4f05d208c95c 100644 --- a/Documentation/devicetree/bindings/regulator/tps65217.txt +++ b/Documentation/devicetree/bindings/regulator/tps65217.txt @@ -26,11 +26,7 @@ Example: ti,pmic-shutdown-controller; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: dcdc1 { - reg = <0>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1800000>; regulator-boot-on; @@ -38,7 +34,6 @@ Example: }; dcdc2_reg: dcdc2 { - reg = <1>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -46,7 +41,6 @@ Example: }; dcdc3_reg: dcc3 { - reg = <2>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <1500000>; regulator-boot-on; @@ -54,7 +48,6 @@ Example: }; ldo1_reg: ldo1 { - reg = <3>; regulator-min-microvolt = <1000000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -62,7 +55,6 @@ Example: }; ldo2_reg: ldo2 { - reg = <4>; regulator-min-microvolt = <900000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -70,7 +62,6 @@ Example: }; ldo3_reg: ldo3 { - reg = <5>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; @@ -78,7 +69,6 @@ Example: }; ldo4_reg: ldo4 { - reg = <6>; regulator-min-microvolt = <1800000>; regulator-max-microvolt = <3300000>; regulator-boot-on; diff --git a/arch/arm/boot/dts/am335x-bone-common.dtsi b/arch/arm/boot/dts/am335x-bone-common.dtsi index f3db13d2d90e..0cc150b87b86 100644 --- a/arch/arm/boot/dts/am335x-bone-common.dtsi +++ b/arch/arm/boot/dts/am335x-bone-common.dtsi @@ -285,8 +285,10 @@ }; }; + +/include/ "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; /* * Configure pmic to enter OFF-state instead of SLEEP-state ("RTC-only * mode") at poweroff. Most BeagleBone versions do not support RTC-only @@ -307,17 +309,12 @@ ti,pmic-shutdown-controller; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; regulator-name = "vdds_dpr"; regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -327,7 +324,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -337,25 +333,21 @@ }; ldo1_reg: regulator@3 { - reg = <3>; regulator-name = "vio,vrtc,vdds"; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; regulator-name = "vdd_3v3aux"; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; regulator-name = "vdd_1v8"; regulator-always-on; }; ldo4_reg: regulator@6 { - reg = <6>; regulator-name = "vdd_3v3a"; regulator-always-on; }; diff --git a/arch/arm/boot/dts/am335x-chilisom.dtsi b/arch/arm/boot/dts/am335x-chilisom.dtsi index fda457b07e15..857d9894103a 100644 --- a/arch/arm/boot/dts/am335x-chilisom.dtsi +++ b/arch/arm/boot/dts/am335x-chilisom.dtsi @@ -128,21 +128,16 @@ }; +/include/ "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; - regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; regulator-name = "vdds_dpr"; regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -152,7 +147,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -162,28 +156,24 @@ }; ldo1_reg: regulator@3 { - reg = <3>; regulator-name = "vio,vrtc,vdds"; regulator-boot-on; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; regulator-name = "vdd_3v3aux"; regulator-boot-on; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; regulator-name = "vdd_1v8"; regulator-boot-on; regulator-always-on; }; ldo4_reg: regulator@6 { - reg = <6>; regulator-name = "vdd_3v3d"; regulator-boot-on; regulator-always-on; diff --git a/arch/arm/boot/dts/am335x-nano.dts b/arch/arm/boot/dts/am335x-nano.dts index 77559a1ded60..f313999c503e 100644 --- a/arch/arm/boot/dts/am335x-nano.dts +++ b/arch/arm/boot/dts/am335x-nano.dts @@ -375,15 +375,11 @@ wp-gpios = <&gpio3 18 0>; }; +#include "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; - regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* +1.5V voltage with ±4% tolerance */ regulator-min-microvolt = <1450000>; regulator-max-microvolt = <1550000>; @@ -392,7 +388,6 @@ }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.1V with ±4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <915000>; @@ -402,7 +397,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with ±4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <915000>; @@ -412,7 +406,6 @@ }; ldo1_reg: regulator@3 { - reg = <3>; /* +1.8V voltage with ±4% tolerance */ regulator-min-microvolt = <1750000>; regulator-max-microvolt = <1870000>; @@ -421,7 +414,6 @@ }; ldo2_reg: regulator@4 { - reg = <4>; /* +3.3V voltage with ±4% tolerance */ regulator-min-microvolt = <3175000>; regulator-max-microvolt = <3430000>; @@ -430,7 +422,6 @@ }; ldo3_reg: regulator@5 { - reg = <5>; /* +1.8V voltage with ±4% tolerance */ regulator-min-microvolt = <1750000>; regulator-max-microvolt = <1870000>; @@ -439,7 +430,6 @@ }; ldo4_reg: regulator@6 { - reg = <6>; /* +3.3V voltage with ±4% tolerance */ regulator-min-microvolt = <3175000>; regulator-max-microvolt = <3430000>; diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts index 471a3a70ea1f..8867aaaec54d 100644 --- a/arch/arm/boot/dts/am335x-pepper.dts +++ b/arch/arm/boot/dts/am335x-pepper.dts @@ -420,9 +420,9 @@ vin-supply = <&vbat>; }; -&tps { - compatible = "ti,tps65217"; +/include/ "tps65217.dtsi" +&tps { backlight { isel = <1>; /* ISET1 */ fdim = <200>; /* TPS65217_BL_FDIM_200HZ */ @@ -430,17 +430,12 @@ }; regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* VDD_1V8 system supply */ regulator-always-on; }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -450,7 +445,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -460,21 +454,18 @@ }; ldo1_reg: regulator@3 { - reg = <3>; /* VRTC 1.8V always-on supply */ regulator-name = "vrtc,vdds"; regulator-always-on; }; ldo2_reg: regulator@4 { - reg = <4>; /* 3.3V rail */ regulator-name = "vdd_3v3aux"; regulator-always-on; }; ldo3_reg: regulator@5 { - reg = <5>; /* VDD_3V3A 3.3V rail */ regulator-name = "vdd_3v3a"; regulator-min-microvolt = <3300000>; @@ -482,7 +473,6 @@ }; ldo4_reg: regulator@6 { - reg = <6>; /* VDD_3V3B 3.3V rail */ regulator-name = "vdd_3v3b"; regulator-always-on; diff --git a/arch/arm/boot/dts/am335x-sl50.dts b/arch/arm/boot/dts/am335x-sl50.dts index d38edfa53bb9..3303c281697b 100644 --- a/arch/arm/boot/dts/am335x-sl50.dts +++ b/arch/arm/boot/dts/am335x-sl50.dts @@ -375,19 +375,16 @@ pinctrl-0 = <&uart4_pins>; }; +#include "tps65217.dtsi" + &tps { - compatible = "ti,tps65217"; ti,pmic-shutdown-controller; interrupt-parent = <&intc>; interrupts = <7>; /* NNMI */ regulators { - #address-cells = <1>; - #size-cells = <0>; - dcdc1_reg: regulator@0 { - reg = <0>; /* VDDS_DDR */ regulator-min-microvolt = <1500000>; regulator-max-microvolt = <1500000>; @@ -395,7 +392,6 @@ }; dcdc2_reg: regulator@1 { - reg = <1>; /* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */ regulator-name = "vdd_mpu"; regulator-min-microvolt = <925000>; @@ -405,7 +401,6 @@ }; dcdc3_reg: regulator@2 { - reg = <2>; /* VDD_CORE voltage limits 0.95V - 1.1V with +/-4% tolerance */ regulator-name = "vdd_core"; regulator-min-microvolt = <925000>; @@ -415,7 +410,6 @@ }; ldo1_reg: regulator@3 { - reg = <3>; /* VRTC / VIO / VDDS*/ regulator-always-on; regulator-min-microvolt = <1800000>; @@ -423,7 +417,6 @@ }; ldo2_reg: regulator@4 { - reg = <4>; /* VDD_3V3AUX */ regulator-always-on; regulator-min-microvolt = <3300000>; @@ -431,7 +424,6 @@ }; ldo3_reg: regulator@5 { - reg = <5>; /* VDD_1V8 */ regulator-min-microvolt = <1800000>; regulator-max-microvolt = <1800000>; @@ -439,7 +431,6 @@ }; ldo4_reg: regulator@6 { - reg = <6>; /* VDD_3V3A */ regulator-min-microvolt = <3300000>; regulator-max-microvolt = <3300000>; diff --git a/arch/arm/boot/dts/tps65217.dtsi b/arch/arm/boot/dts/tps65217.dtsi new file mode 100644 index 000000000000..a63272422d76 --- /dev/null +++ b/arch/arm/boot/dts/tps65217.dtsi @@ -0,0 +1,56 @@ +/* + * Copyright (C) 2012 Texas Instruments Incorporated - http://www.ti.com/ + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* + * Integrated Power Management Chip + * http://www.ti.com/lit/ds/symlink/tps65217.pdf + */ + +&tps { + compatible = "ti,tps65217"; + + regulators { + #address-cells = <1>; + #size-cells = <0>; + + dcdc1_reg: regulator@0 { + reg = <0>; + regulator-compatible = "dcdc1"; + }; + + dcdc2_reg: regulator@1 { + reg = <1>; + regulator-compatible = "dcdc2"; + }; + + dcdc3_reg: regulator@2 { + reg = <2>; + regulator-compatible = "dcdc3"; + }; + + ldo1_reg: regulator@3 { + reg = <3>; + regulator-compatible = "ldo1"; + }; + + ldo2_reg: regulator@4 { + reg = <4>; + regulator-compatible = "ldo2"; + }; + + ldo3_reg: regulator@5 { + reg = <5>; + regulator-compatible = "ldo3"; + }; + + ldo4_reg: regulator@6 { + reg = <6>; + regulator-compatible = "ldo4"; + }; + }; +}; From 9a154c8911e39e32bdbc2cd6c9b08a64e17612aa Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 11 Dec 2015 14:36:17 -0500 Subject: [PATCH 333/489] ftracetest: Fix instance test to use proper shell command for pids The ftracetest instance test used parsing of the "jobs" output to find the pid of the subshell that is executed previously. But this is not portable to all major shells that may run these tests. The proper way to get the pid of the subshell is the shell command "$!". This will return the pid of the previously executed command. Use that instead, otherwise the test does not work in all environments. Link: http://lkml.kernel.org/r/20151211143617.65f4d7a1@gandalf.local.home Reported-by: Michael Ellerman Signed-off-by: Steven Rostedt --- .../selftests/ftrace/test.d/instances/instance.tc | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/ftrace/test.d/instances/instance.tc b/tools/testing/selftests/ftrace/test.d/instances/instance.tc index 773e276ff90b..1e1abe0ad354 100644 --- a/tools/testing/selftests/ftrace/test.d/instances/instance.tc +++ b/tools/testing/selftests/ftrace/test.d/instances/instance.tc @@ -39,28 +39,23 @@ instance_slam() { } instance_slam & -x=`jobs -l` -p1=`echo $x | cut -d' ' -f2` +p1=$! echo $p1 instance_slam & -x=`jobs -l | tail -1` -p2=`echo $x | cut -d' ' -f2` +p2=$! echo $p2 instance_slam & -x=`jobs -l | tail -1` -p3=`echo $x | cut -d' ' -f2` +p3=$! echo $p3 instance_slam & -x=`jobs -l | tail -1` -p4=`echo $x | cut -d' ' -f2` +p4=$! echo $p4 instance_slam & -x=`jobs -l | tail -1` -p5=`echo $x | cut -d' ' -f2` +p5=$! echo $p5 ls -lR >/dev/null From 6e22c8366416251a3d88ba6c92d13d595089f0ed Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 12 Feb 2016 12:46:00 -0800 Subject: [PATCH 334/489] tracing, kasan: Silence Kasan warning in check_stack of stack_tracer When enabling stack trace via "echo 1 > /proc/sys/kernel/stack_tracer_enabled", the below KASAN warning is triggered: BUG: KASAN: stack-out-of-bounds in check_stack+0x344/0x848 at addr ffffffc0689ebab8 Read of size 8 by task ksoftirqd/4/29 page:ffffffbdc3a27ac0 count:0 mapcount:0 mapping: (null) index:0x0 flags: 0x0() page dumped because: kasan: bad access detected CPU: 4 PID: 29 Comm: ksoftirqd/4 Not tainted 4.5.0-rc1 #129 Hardware name: Freescale Layerscape 2085a RDB Board (DT) Call trace: [] dump_backtrace+0x0/0x3a0 [] show_stack+0x24/0x30 [] dump_stack+0xd8/0x168 [] kasan_report_error+0x6a0/0x920 [] kasan_report+0x70/0xb8 [] __asan_load8+0x60/0x78 [] check_stack+0x344/0x848 [] stack_trace_call+0x1c4/0x370 [] ftrace_ops_no_ops+0x2c0/0x590 [] ftrace_graph_call+0x0/0x14 [] fpsimd_thread_switch+0x24/0x1e8 [] __switch_to+0x34/0x218 [] __schedule+0x3ac/0x15b8 [] schedule+0x5c/0x178 [] smpboot_thread_fn+0x350/0x960 [] kthread+0x1d8/0x2b0 [] ret_from_fork+0x10/0x40 Memory state around the buggy address: ffffffc0689eb980: 00 00 00 00 00 00 00 00 f1 f1 f1 f1 00 f4 f4 f4 ffffffc0689eba00: f3 f3 f3 f3 00 00 00 00 00 00 00 00 00 00 00 00 >ffffffc0689eba80: 00 00 f1 f1 f1 f1 00 f4 f4 f4 f3 f3 f3 f3 00 00 ^ ffffffc0689ebb00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffffffc0689ebb80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 The stacker tracer traverses the whole kernel stack when saving the max stack trace. It may touch the stack red zones to cause the warning. So, just disable the instrumentation to silence the warning. Link: http://lkml.kernel.org/r/1455309960-18930-1-git-send-email-yang.shi@linaro.org Signed-off-by: Yang Shi Signed-off-by: Steven Rostedt --- kernel/trace/trace_stack.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 202df6cffcca..2a1abbaca10e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -156,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack) for (; p < top && i < stack_trace_max.nr_entries; p++) { if (stack_dump_trace[i] == ULONG_MAX) break; - if (*p == stack_dump_trace[i]) { + /* + * The READ_ONCE_NOCHECK is used to let KASAN know that + * this is not a stack-out-of-bounds error. + */ + if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) { stack_dump_trace[x] = stack_dump_trace[i++]; this_size = stack_trace_index[x++] = (top - p) * sizeof(unsigned long); From 6697b2cf69d4363266ca47eaebc49ef13dabc1c9 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Thu, 4 Feb 2016 16:51:00 -0800 Subject: [PATCH 335/489] nfit: fix multi-interface dimm handling, acpi6.1 compatibility ACPI 6.1 clarified that multi-interface dimms require multiple control region entries (DCRs) per dimm. Previously we were assuming that a control region is only present when block-data-windows are present. This implementation was done with an eye to be compatibility with the looser ACPI 6.0 interpretation of this table. 1/ When coalescing the memory device (MEMDEV) tables for a single dimm, coalesce on device_handle rather than control region index. 2/ Whenever we disocver a control region with non-zero block windows re-scan for block-data-window (BDW) entries. We may need to revisit this if a DIMM ever implements a format interface outside of blk or pmem, but that is not on the foreseeable horizon. Cc: Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 71 ++++++++++++++++++++++----------------------- 1 file changed, 35 insertions(+), 36 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index ad6d8c6b777e..424b362e8fdc 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -469,37 +469,16 @@ static void nfit_mem_find_spa_bdw(struct acpi_nfit_desc *acpi_desc, nfit_mem->bdw = NULL; } -static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, +static void nfit_mem_init_bdw(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, struct acpi_nfit_system_address *spa) { u16 dcr = __to_nfit_memdev(nfit_mem)->region_index; struct nfit_memdev *nfit_memdev; struct nfit_flush *nfit_flush; - struct nfit_dcr *nfit_dcr; struct nfit_bdw *nfit_bdw; struct nfit_idt *nfit_idt; u16 idt_idx, range_index; - list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { - if (nfit_dcr->dcr->region_index != dcr) - continue; - nfit_mem->dcr = nfit_dcr->dcr; - break; - } - - if (!nfit_mem->dcr) { - dev_dbg(acpi_desc->dev, "SPA %d missing:%s%s\n", - spa->range_index, __to_nfit_memdev(nfit_mem) - ? "" : " MEMDEV", nfit_mem->dcr ? "" : " DCR"); - return -ENODEV; - } - - /* - * We've found enough to create an nvdimm, optionally - * find an associated BDW - */ - list_add(&nfit_mem->list, &acpi_desc->dimms); - list_for_each_entry(nfit_bdw, &acpi_desc->bdws, list) { if (nfit_bdw->bdw->region_index != dcr) continue; @@ -508,12 +487,12 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } if (!nfit_mem->bdw) - return 0; + return; nfit_mem_find_spa_bdw(acpi_desc, nfit_mem); if (!nfit_mem->spa_bdw) - return 0; + return; range_index = nfit_mem->spa_bdw->range_index; list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { @@ -538,8 +517,6 @@ static int nfit_mem_add(struct acpi_nfit_desc *acpi_desc, } break; } - - return 0; } static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, @@ -548,7 +525,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, struct nfit_mem *nfit_mem, *found; struct nfit_memdev *nfit_memdev; int type = nfit_spa_type(spa); - u16 dcr; switch (type) { case NFIT_SPA_DCR: @@ -559,14 +535,18 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, } list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { - int rc; + struct nfit_dcr *nfit_dcr; + u32 device_handle; + u16 dcr; if (nfit_memdev->memdev->range_index != spa->range_index) continue; found = NULL; dcr = nfit_memdev->memdev->region_index; + device_handle = nfit_memdev->memdev->device_handle; list_for_each_entry(nfit_mem, &acpi_desc->dimms, list) - if (__to_nfit_memdev(nfit_mem)->region_index == dcr) { + if (__to_nfit_memdev(nfit_mem)->device_handle + == device_handle) { found = nfit_mem; break; } @@ -579,6 +559,31 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, if (!nfit_mem) return -ENOMEM; INIT_LIST_HEAD(&nfit_mem->list); + list_add(&nfit_mem->list, &acpi_desc->dimms); + } + + list_for_each_entry(nfit_dcr, &acpi_desc->dcrs, list) { + if (nfit_dcr->dcr->region_index != dcr) + continue; + /* + * Record the control region for the dimm. For + * the ACPI 6.1 case, where there are separate + * control regions for the pmem vs blk + * interfaces, be sure to record the extended + * blk details. + */ + if (!nfit_mem->dcr) + nfit_mem->dcr = nfit_dcr->dcr; + else if (nfit_mem->dcr->windows == 0 + && nfit_dcr->dcr->windows) + nfit_mem->dcr = nfit_dcr->dcr; + break; + } + + if (dcr && !nfit_mem->dcr) { + dev_err(acpi_desc->dev, "SPA %d missing DCR %d\n", + spa->range_index, dcr); + return -ENODEV; } if (type == NFIT_SPA_DCR) { @@ -595,6 +600,7 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, nfit_mem->idt_dcr = nfit_idt->idt; break; } + nfit_mem_init_bdw(acpi_desc, nfit_mem, spa); } else { /* * A single dimm may belong to multiple SPA-PM @@ -603,13 +609,6 @@ static int nfit_mem_dcr_init(struct acpi_nfit_desc *acpi_desc, */ nfit_mem->memdev_pmem = nfit_memdev->memdev; } - - if (found) - continue; - - rc = nfit_mem_add(acpi_desc, nfit_mem, spa); - if (rc) - return rc; } return 0; From cfdd28beb3205dbd1e91571516807199c8ab84ca Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Wed, 17 Feb 2016 18:00:31 +0100 Subject: [PATCH 336/489] net: make netdev_for_each_lower_dev safe for device removal When I used netdev_for_each_lower_dev in commit bad531623253 ("vrf: remove slave queue and private slave struct") I thought that it acts like netdev_for_each_lower_private and can be used to remove the current device from the list while walking, but unfortunately it acts more like netdev_for_each_lower_private_rcu and doesn't allow it. The difference is where the "iter" points to, right now it points to the current element and that makes it impossible to remove it. Change the logic to be similar to netdev_for_each_lower_private and make it point to the "next" element so we can safely delete the current one. VRF is the only such user right now, there's no change for the read-only users. Here's what can happen now: [98423.249858] general protection fault: 0000 [#1] SMP [98423.250175] Modules linked in: vrf bridge(O) stp llc nfsd auth_rpcgss oid_registry nfs_acl nfs lockd grace sunrpc crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel jitterentropy_rng sha256_generic hmac drbg ppdev aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd evdev serio_raw pcspkr virtio_balloon parport_pc parport i2c_piix4 i2c_core virtio_console acpi_cpufreq button 9pnet_virtio 9p 9pnet fscache ipv6 autofs4 ext4 crc16 mbcache jbd2 sg virtio_blk virtio_net sr_mod cdrom e1000 ata_generic ehci_pci uhci_hcd ehci_hcd usbcore usb_common virtio_pci ata_piix libata floppy virtio_ring virtio scsi_mod [last unloaded: bridge] [98423.255040] CPU: 1 PID: 14173 Comm: ip Tainted: G O 4.5.0-rc2+ #81 [98423.255386] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.8.1-20150318_183358- 04/01/2014 [98423.255777] task: ffff8800547f5540 ti: ffff88003428c000 task.ti: ffff88003428c000 [98423.256123] RIP: 0010:[] [] netdev_lower_get_next+0x1e/0x30 [98423.256534] RSP: 0018:ffff88003428f940 EFLAGS: 00010207 [98423.256766] RAX: 0002000100000004 RBX: ffff880054ff9000 RCX: 0000000000000000 [98423.257039] RDX: ffff88003428f8b8 RSI: ffff88003428f950 RDI: ffff880054ff90c0 [98423.257287] RBP: ffff88003428f940 R08: 0000000000000000 R09: 0000000000000000 [98423.257537] R10: 0000000000000001 R11: 0000000000000000 R12: ffff88003428f9e0 [98423.257802] R13: ffff880054a5fd00 R14: ffff88003428f970 R15: 0000000000000001 [98423.258055] FS: 00007f3d76881700(0000) GS:ffff88005d000000(0000) knlGS:0000000000000000 [98423.258418] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [98423.258650] CR2: 00007ffe5951ffa8 CR3: 0000000052077000 CR4: 00000000000406e0 [98423.258902] Stack: [98423.259075] ffff88003428f960 ffffffffa0442636 0002000100000004 ffff880054ff9000 [98423.259647] ffff88003428f9b0 ffffffff81518205 ffff880054ff9000 ffff88003428f978 [98423.260208] ffff88003428f978 ffff88003428f9e0 ffff88003428f9e0 ffff880035b35f00 [98423.260739] Call Trace: [98423.260920] [] vrf_dev_uninit+0x76/0xa0 [vrf] [98423.261156] [] rollback_registered_many+0x205/0x390 [98423.261401] [] unregister_netdevice_many+0x1c/0x70 [98423.261641] [] rtnl_delete_link+0x3c/0x50 [98423.271557] [] rtnl_dellink+0xcb/0x1d0 [98423.271800] [] ? __inc_zone_state+0x4a/0x90 [98423.272049] [] rtnetlink_rcv_msg+0x84/0x200 [98423.272279] [] ? trace_hardirqs_on+0xd/0x10 [98423.272513] [] ? rtnetlink_rcv+0x1b/0x40 [98423.272755] [] ? rtnetlink_rcv+0x40/0x40 [98423.272983] [] netlink_rcv_skb+0x97/0xb0 [98423.273209] [] rtnetlink_rcv+0x2a/0x40 [98423.273476] [] netlink_unicast+0x11b/0x1a0 [98423.273710] [] netlink_sendmsg+0x3e1/0x610 [98423.273947] [] sock_sendmsg+0x38/0x70 [98423.274175] [] ___sys_sendmsg+0x2e3/0x2f0 [98423.274416] [] ? do_raw_spin_unlock+0xbe/0x140 [98423.274658] [] ? handle_mm_fault+0x26c/0x2210 [98423.274894] [] ? handle_mm_fault+0x4d/0x2210 [98423.275130] [] ? __fget_light+0x91/0xb0 [98423.275365] [] __sys_sendmsg+0x42/0x80 [98423.275595] [] SyS_sendmsg+0x12/0x20 [98423.275827] [] entry_SYSCALL_64_fastpath+0x16/0x7a [98423.276073] Code: c3 31 c0 5d c3 0f 1f 84 00 00 00 00 00 66 66 66 66 90 48 8b 06 55 48 81 c7 c0 00 00 00 48 89 e5 48 8b 00 48 39 f8 74 09 48 89 06 <48> 8b 40 e8 5d c3 31 c0 5d c3 0f 1f 84 00 00 00 00 00 66 66 66 [98423.279639] RIP [] netdev_lower_get_next+0x1e/0x30 [98423.279920] RSP CC: David Ahern CC: David S. Miller CC: Roopa Prabhu CC: Vlad Yasevich Fixes: bad531623253 ("vrf: remove slave queue and private slave struct") Signed-off-by: Nikolay Aleksandrov Reviewed-by: David Ahern Tested-by: David Ahern Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 289c2314d766..5440b7b705eb 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3718,7 +3718,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_dev(dev, ldev, iter) \ - for (iter = &(dev)->adj_list.lower, \ + for (iter = (dev)->adj_list.lower.next, \ ldev = netdev_lower_get_next(dev, &(iter)); \ ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) diff --git a/net/core/dev.c b/net/core/dev.c index e15e6e6a7a8a..0ef061b2badc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5379,12 +5379,12 @@ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; - lower = list_entry((*iter)->next, struct netdev_adjacent, list); + lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; - *iter = &lower->list; + *iter = lower->list.next; return lower->dev; } From a97eb33ff225f34a8124774b3373fd244f0e83ce Mon Sep 17 00:00:00 2001 From: Anton Protopopov Date: Tue, 16 Feb 2016 21:43:16 -0500 Subject: [PATCH 337/489] rtnl: RTM_GETNETCONF: fix wrong return value An error response from a RTM_GETNETCONF request can return the positive error value EINVAL in the struct nlmsgerr that can mislead userspace. Signed-off-by: Anton Protopopov Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/ipv4/devinet.c | 2 +- net/ipv6/addrconf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index cebd9d31e65a..f6303b17546b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9efd9ffdc34c..bdd7eac4307a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -583,7 +583,7 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = EINVAL; + err = -EINVAL; if (!tb[NETCONFA_IFINDEX]) goto errout; From b53ce3e7d407aa4196877a48b8601181162ab158 Mon Sep 17 00:00:00 2001 From: Insu Yun Date: Wed, 17 Feb 2016 11:47:35 -0500 Subject: [PATCH 338/489] tipc: unlock in error path tipc_bcast_unlock need to be unlocked in error path. Signed-off-by: Insu Yun Signed-off-by: David S. Miller --- net/tipc/link.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/net/tipc/link.c b/net/tipc/link.c index 0c2944fb9ae0..347cdc99ed09 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1973,8 +1973,10 @@ int tipc_nl_add_bc_link(struct net *net, struct tipc_nl_msg *msg) hdr = genlmsg_put(msg->skb, msg->portid, msg->seq, &tipc_genl_family, NLM_F_MULTI, TIPC_NL_LINK_GET); - if (!hdr) + if (!hdr) { + tipc_bcast_unlock(net); return -EMSGSIZE; + } attrs = nla_nest_start(msg->skb, TIPC_NLA_LINK); if (!attrs) From c868ee7063bdb53f3ef9eac7bcec84960980b471 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 17 Feb 2016 19:30:01 +0100 Subject: [PATCH 339/489] lwt: fix rx checksum setting for lwt devices tunneling over ipv6 the commit 35e2d1152b22 ("tunnels: Allow IPv6 UDP checksums to be correctly controlled.") changed the default xmit checksum setting for lwt vxlan/geneve ipv6 tunnels, so that now the checksum is not set into external UDP header. This commit changes the rx checksum setting for both lwt vxlan/geneve devices created by openvswitch accordingly, so that lwt over ipv6 tunnel pairs are again able to communicate with default values. Signed-off-by: Paolo Abeni Acked-by: Jiri Benc Acked-by: Jesse Gross Signed-off-by: David S. Miller --- drivers/net/geneve.c | 3 ++- net/openvswitch/vport-vxlan.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 4a9cc038c4b0..0bf7edd99573 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1470,7 +1470,8 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, return dev; err = geneve_configure(net, dev, &geneve_remote_unspec, - 0, 0, 0, htons(dst_port), true, 0); + 0, 0, 0, htons(dst_port), true, + GENEVE_F_UDP_ZERO_CSUM6_RX); if (err) goto err; diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index de9cb19efb6a..5eb7694348b5 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -90,7 +90,7 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) int err; struct vxlan_config conf = { .no_share = true, - .flags = VXLAN_F_COLLECT_METADATA, + .flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX, /* Don't restrict the packets that can be sent by MTU */ .mtu = IP_MAX_MTU, }; From 1003e19c466dc37812b5f88b2d5308ee63bb3fa0 Mon Sep 17 00:00:00 2001 From: Steve Wise Date: Thu, 18 Feb 2016 06:34:24 -0800 Subject: [PATCH 340/489] cxgb3: fix up vpd strings for kstrto*() The vpd strings are left justified, in a fixed length array, with possible trailing white space and no NUL. So fix them up before calling kstrto*(). This is a recent regression which causes cxgb3 to fail to load. Fixes: e72c932 ("cxgb3: Convert simple_strtoul to kstrtox") Signed-off-by: Steve Wise Signed-off-by: David S. Miller --- drivers/net/ethernet/chelsio/cxgb3/t3_hw.c | 34 +++++++++++++++++----- 1 file changed, 27 insertions(+), 7 deletions(-) diff --git a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c index ee04caa6c4d8..a89721fad633 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb3/t3_hw.c @@ -681,6 +681,24 @@ int t3_seeprom_wp(struct adapter *adapter, int enable) return t3_seeprom_write(adapter, EEPROM_STAT_ADDR, enable ? 0xc : 0); } +static int vpdstrtouint(char *s, int len, unsigned int base, unsigned int *val) +{ + char tok[len + 1]; + + memcpy(tok, s, len); + tok[len] = 0; + return kstrtouint(strim(tok), base, val); +} + +static int vpdstrtou16(char *s, int len, unsigned int base, u16 *val) +{ + char tok[len + 1]; + + memcpy(tok, s, len); + tok[len] = 0; + return kstrtou16(strim(tok), base, val); +} + /** * get_vpd_params - read VPD parameters from VPD EEPROM * @adapter: adapter to read @@ -709,19 +727,19 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p) return ret; } - ret = kstrtouint(vpd.cclk_data, 10, &p->cclk); + ret = vpdstrtouint(vpd.cclk_data, vpd.cclk_len, 10, &p->cclk); if (ret) return ret; - ret = kstrtouint(vpd.mclk_data, 10, &p->mclk); + ret = vpdstrtouint(vpd.mclk_data, vpd.mclk_len, 10, &p->mclk); if (ret) return ret; - ret = kstrtouint(vpd.uclk_data, 10, &p->uclk); + ret = vpdstrtouint(vpd.uclk_data, vpd.uclk_len, 10, &p->uclk); if (ret) return ret; - ret = kstrtouint(vpd.mdc_data, 10, &p->mdc); + ret = vpdstrtouint(vpd.mdc_data, vpd.mdc_len, 10, &p->mdc); if (ret) return ret; - ret = kstrtouint(vpd.mt_data, 10, &p->mem_timing); + ret = vpdstrtouint(vpd.mt_data, vpd.mt_len, 10, &p->mem_timing); if (ret) return ret; memcpy(p->sn, vpd.sn_data, SERNUM_LEN); @@ -733,10 +751,12 @@ static int get_vpd_params(struct adapter *adapter, struct vpd_params *p) } else { p->port_type[0] = hex_to_bin(vpd.port0_data[0]); p->port_type[1] = hex_to_bin(vpd.port1_data[0]); - ret = kstrtou16(vpd.xaui0cfg_data, 16, &p->xauicfg[0]); + ret = vpdstrtou16(vpd.xaui0cfg_data, vpd.xaui0cfg_len, 16, + &p->xauicfg[0]); if (ret) return ret; - ret = kstrtou16(vpd.xaui1cfg_data, 16, &p->xauicfg[1]); + ret = vpdstrtou16(vpd.xaui1cfg_data, vpd.xaui1cfg_len, 16, + &p->xauicfg[1]); if (ret) return ret; } From 8d2c3ab4445640957d136caa3629857d63544a2a Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Thu, 18 Feb 2016 21:29:08 +0100 Subject: [PATCH 341/489] ser_gigaset: use container_of() instead of detour The purpose of gigaset_device_release() is to kfree() the struct ser_cardstate that contains our struct device. This is done via a bit of a detour. First we make our struct device's driver_data point to the container of our struct ser_cardstate (which is a struct cardstate). In gigaset_device_release() we then retrieve that driver_data again. And after that we finally kfree() the struct ser_cardstate that was saved in the struct cardstate. All of this can be achieved much easier by using container_of() to get from our struct device to its container, struct ser_cardstate. Do so. Note that at the time the detour was implemented commit b8b2c7d845d5 ("base/platform: assert that dev_pm_domain callbacks are called unconditionally") had just entered the tree. That commit disconnected our platform_device and our platform_driver. These were reconnected again in v4.5-rc2 through commit 25cad69f21f5 ("base/platform: Fix platform drivers with no probe callback"). And one of the consequences of that fix was that it broke the detour via driver_data. That's because it made __device_release_driver() stop being a NOP for our struct device and actually do stuff again. One of the things it now does, is setting our driver_data to NULL. That, in turn, makes it impossible for gigaset_device_release() to get to our struct cardstate. Which has the net effect of leaking a struct ser_cardstate at every call of this driver's tty close() operation. So using container_of() has the additional benefit of actually working. Reported-by: Dmitry Vyukov Tested-by: Dmitry Vyukov Signed-off-by: Paul Bolle Acked-by: Tilman Schmidt Signed-off-by: David S. Miller --- drivers/isdn/gigaset/ser-gigaset.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c index 2a506fe0c8a4..d1f8ab915b15 100644 --- a/drivers/isdn/gigaset/ser-gigaset.c +++ b/drivers/isdn/gigaset/ser-gigaset.c @@ -373,13 +373,7 @@ static void gigaset_freecshw(struct cardstate *cs) static void gigaset_device_release(struct device *dev) { - struct cardstate *cs = dev_get_drvdata(dev); - - if (!cs) - return; - dev_set_drvdata(dev, NULL); - kfree(cs->hw.ser); - cs->hw.ser = NULL; + kfree(container_of(dev, struct ser_cardstate, dev.dev)); } /* @@ -408,7 +402,6 @@ static int gigaset_initcshw(struct cardstate *cs) cs->hw.ser = NULL; return rc; } - dev_set_drvdata(&cs->hw.ser->dev.dev, cs); tasklet_init(&cs->write_tasklet, gigaset_modem_fill, (unsigned long) cs); From e817c2f33efb4aa7f02c98dfab9a5f8ff383ea7e Mon Sep 17 00:00:00 2001 From: Andreas Gruenbacher Date: Thu, 18 Feb 2016 12:04:08 +0100 Subject: [PATCH 342/489] selinux: Don't sleep inside inode_getsecid hook The inode_getsecid hook is called from contexts in which sleeping is not allowed, so we cannot revalidate inode security labels from there. Use the non-validating version of inode_security() instead. Reported-by: Benjamin Coddington Signed-off-by: Andreas Gruenbacher Acked-by: Stephen Smalley Signed-off-by: Paul Moore --- security/selinux/hooks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f8110cfd80ff..f1ab71504e1d 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3249,7 +3249,7 @@ static int selinux_inode_listsecurity(struct inode *inode, char *buffer, size_t static void selinux_inode_getsecid(struct inode *inode, u32 *secid) { - struct inode_security_struct *isec = inode_security(inode); + struct inode_security_struct *isec = inode_security_novalidate(inode); *secid = isec->sid; } From 2b8341b3f917c108b47f6a8a771a40d226c57883 Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 19 Feb 2016 02:06:38 +0100 Subject: [PATCH 343/489] drm/radeon: Don't hang in radeon_flip_work_func on disabled crtc. (v2) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a regression introduced in Linux 4.4. Limit the amount of time radeon_flip_work_func can delay programming a page flip, by both limiting the maximum amount of time per wait cycle and the maximum number of wait cycles. Continue the flip if the limit is exceeded, even if that may result in a visual or timing glitch. This is to prevent a hang of page flips, as reported in fdo bug #93746: Disconnecting a DisplayPort display in parallel to a kms pageflip getting queued can cause the following hang of page flips and thereby an unusable desktop: 1. kms pageflip ioctl() queues pageflip -> queues execution of radeon_flip_work_func. 2. Hotunplug of display causes the driver to DPMS OFF the unplugged display. Display engine shuts down, scanout no longer moves, but stays at its resting position at start line of vblank. 3. radeon_flip_work_func executes while crtc is off, and due to the non-moving scanout position, the new flip delay code introduced into Linux 4.4 by commit 5b5561b3660d ("drm/radeon: Fixup hw vblank counter/ts..") enters an infinite wait loop. 4. After reconnecting the display, the pageflip continues to hang in 3. and the display doesn't update its view of the desktop. This patch fixes the Linux 4.4 regression from fdo bug #93746 v2: Skip wait immediately if !radeon_crtc->enabled, as suggested by Michel. Reported-by: Bernd Steinhauser Signed-off-by: Mario Kleiner Tested-by: Bernd Steinhauser Cc: # 4.4+ Cc: Michel Dänzer Cc: Alex Deucher Reviewed-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/radeon/radeon_display.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c index 298ea1c453c3..2b9ba03a7c1a 100644 --- a/drivers/gpu/drm/radeon/radeon_display.c +++ b/drivers/gpu/drm/radeon/radeon_display.c @@ -403,7 +403,8 @@ static void radeon_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &radeon_crtc->base; unsigned long flags; int r; - int vpos, hpos, stat, min_udelay; + int vpos, hpos, stat, min_udelay = 0; + unsigned repcnt = 4; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; down_read(&rdev->exclusive_lock); @@ -454,7 +455,7 @@ static void radeon_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (radeon_crtc->enabled && repcnt--) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -472,10 +473,22 @@ static void radeon_flip_work_func(struct work_struct *__work) /* Sleep at least until estimated real start of hw vblank */ spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ radeon_page_flip(rdev, radeon_crtc->crtc_id, work->base); From e1d09dc0ccc6c91e3916476f636edb76da1f65bb Mon Sep 17 00:00:00 2001 From: Mario Kleiner Date: Fri, 19 Feb 2016 02:06:39 +0100 Subject: [PATCH 344/489] drm/amdgpu: Don't hang in amdgpu_flip_work_func on disabled crtc. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This fixes a regression introduced in Linux 4.4. This is a port of the same fix for radeon-kms in the patch "drm/radeon: Don't hang in radeon_flip_work_func on disabled crtc. (v2)" Limit the amount of time amdgpu_flip_work_func can delay programming a page flip, by both limiting the maximum amount of time per wait cycle and the maximum number of wait cycles. Continue the flip if the limit is exceeded, even if that may result in a visual or timing glitch. This is to prevent a hang of page flips, as reported in fdo bug #93746: Disconnecting a DisplayPort display in parallel to a kms pageflip getting queued can cause the following hang of page flips and thereby an unusable desktop: 1. kms pageflip ioctl() queues pageflip -> queues execution of amdgpu_flip_work_func. 2. Hotunplug of display causes the driver to DPMS OFF the unplugged display. Display engine shuts down, scanout no longer moves, but stays at its resting position at start line of vblank. 3. amdgpu_flip_work_func executes while crtc is off, and due to the non-moving scanout position, the new flip delay code introduced into Linux 4.4 by commit 8e36f9d33c13 ("drm/amdgpu: Fixup hw vblank counter/ts..") enters an infinite wait loop. 4. After reconnecting the display, the pageflip continues to hang in 3. and the display doesn't update its view of the desktop. This patch fixes the Linux 4.4 regression from fdo bug #93746 Reported-by: Bernd Steinhauser Signed-off-by: Mario Kleiner Cc: # 4.4+ Cc: Michel Dänzer Cc: Alex Deucher Reviewed-by: Michel Dänzer Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index acd066d0a805..8297bc319369 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -72,8 +72,8 @@ static void amdgpu_flip_work_func(struct work_struct *__work) struct drm_crtc *crtc = &amdgpuCrtc->base; unsigned long flags; - unsigned i; - int vpos, hpos, stat, min_udelay; + unsigned i, repcnt = 4; + int vpos, hpos, stat, min_udelay = 0; struct drm_vblank_crtc *vblank = &crtc->dev->vblank[work->crtc_id]; amdgpu_flip_wait_fence(adev, &work->excl); @@ -96,7 +96,7 @@ static void amdgpu_flip_work_func(struct work_struct *__work) * In practice this won't execute very often unless on very fast * machines because the time window for this to happen is very small. */ - for (;;) { + while (amdgpuCrtc->enabled && repcnt--) { /* GET_DISTANCE_TO_VBLANKSTART returns distance to real vblank * start in hpos, and to the "fudged earlier" vblank start in * vpos. @@ -114,10 +114,22 @@ static void amdgpu_flip_work_func(struct work_struct *__work) /* Sleep at least until estimated real start of hw vblank */ spin_unlock_irqrestore(&crtc->dev->event_lock, flags); min_udelay = (-hpos + 1) * max(vblank->linedur_ns / 1000, 5); + if (min_udelay > vblank->framedur_ns / 2000) { + /* Don't wait ridiculously long - something is wrong */ + repcnt = 0; + break; + } usleep_range(min_udelay, 2 * min_udelay); spin_lock_irqsave(&crtc->dev->event_lock, flags); }; + if (!repcnt) + DRM_DEBUG_DRIVER("Delay problem on crtc %d: min_udelay %d, " + "framedur %d, linedur %d, stat %d, vpos %d, " + "hpos %d\n", work->crtc_id, min_udelay, + vblank->framedur_ns / 1000, + vblank->linedur_ns / 1000, stat, vpos, hpos); + /* do the flip (mmio) */ adev->mode_info.funcs->page_flip(adev, work->crtc_id, work->base); /* set the flip status */ From 747ffe11b440ef9ea752888806d3aac677ca52a4 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 19 Feb 2016 15:21:14 -0800 Subject: [PATCH 345/489] libnvdimm, tools/testing/nvdimm: fix 'ars_status' output buffer sizing Use the output length specified in the command to size the receive buffer rather than the arbitrary 4K limit. This bug was hiding the fact that the ndctl implementation of ndctl_bus_cmd_new_ars_status() was not specifying an output buffer size. Cc: Cc: Vishal Verma Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 13 +++++++------ drivers/nvdimm/bus.c | 8 ++++---- include/linux/libnvdimm.h | 1 - tools/testing/nvdimm/test/nfit.c | 8 ++++++-- 4 files changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 424b362e8fdc..1d4b9c6bdf45 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1516,13 +1516,13 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, } static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, - struct nd_cmd_ars_status *cmd) + struct nd_cmd_ars_status *cmd, u32 size) { int rc; while (1) { rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd, - sizeof(*cmd)); + size); if (rc || cmd->status & 0xffff) return -ENXIO; @@ -1580,6 +1580,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, struct nd_cmd_ars_start *ars_start = NULL; struct nd_cmd_ars_cap *ars_cap = NULL; u64 start, len, cur, remaining; + u32 ars_status_size; int rc; ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL); @@ -1609,14 +1610,14 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, * Check if a full-range ARS has been run. If so, use those results * without having to start a new ARS. */ - ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status), - GFP_KERNEL); + ars_status_size = ars_cap->max_ars_out; + ars_status = kzalloc(ars_status_size, GFP_KERNEL); if (!ars_status) { rc = -ENOMEM; goto out; } - rc = ars_get_status(nd_desc, ars_status); + rc = ars_get_status(nd_desc, ars_status, ars_status_size); if (rc) goto out; @@ -1646,7 +1647,7 @@ static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, if (rc) goto out; - rc = ars_get_status(nd_desc, ars_status); + rc = ars_get_status(nd_desc, ars_status, ars_status_size); if (rc) goto out; diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 7e2c43f701bc..99953b34fa1d 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -392,8 +392,8 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { .out_sizes = { 4, }, }, [ND_CMD_ARS_STATUS] = { - .out_num = 2, - .out_sizes = { 4, UINT_MAX, }, + .out_num = 3, + .out_sizes = { 4, 4, UINT_MAX, }, }, }; @@ -442,8 +442,8 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, return in_field[1]; else if (nvdimm && cmd == ND_CMD_VENDOR && idx == 2) return out_field[1]; - else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 1) - return ND_CMD_ARS_STATUS_MAX; + else if (!nvdimm && cmd == ND_CMD_ARS_STATUS && idx == 2) + return out_field[1] - 8; return UINT_MAX; } diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index bed40dff0e86..c736382fd260 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -28,7 +28,6 @@ enum { ND_IOCTL_MAX_BUFLEN = SZ_4M, ND_CMD_MAX_ELEM = 4, ND_CMD_MAX_ENVELOPE = 16, - ND_CMD_ARS_STATUS_MAX = SZ_4K, ND_MAX_MAPPINGS = 32, /* region flag indicating to direct-map persistent memory by default */ diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c index 90bd2ea41032..b3281dcd4a5d 100644 --- a/tools/testing/nvdimm/test/nfit.c +++ b/tools/testing/nvdimm/test/nfit.c @@ -217,13 +217,16 @@ static int nfit_test_cmd_set_config_data(struct nd_cmd_set_config_hdr *nd_cmd, return rc; } +#define NFIT_TEST_ARS_RECORDS 4 + static int nfit_test_cmd_ars_cap(struct nd_cmd_ars_cap *nd_cmd, unsigned int buf_len) { if (buf_len < sizeof(*nd_cmd)) return -EINVAL; - nd_cmd->max_ars_out = 256; + nd_cmd->max_ars_out = sizeof(struct nd_cmd_ars_status) + + NFIT_TEST_ARS_RECORDS * sizeof(struct nd_ars_record); nd_cmd->status = (ND_ARS_PERSISTENT | ND_ARS_VOLATILE) << 16; return 0; @@ -246,7 +249,8 @@ static int nfit_test_cmd_ars_status(struct nd_cmd_ars_status *nd_cmd, if (buf_len < sizeof(*nd_cmd)) return -EINVAL; - nd_cmd->out_length = 256; + nd_cmd->out_length = sizeof(struct nd_cmd_ars_status); + /* TODO: emit error records */ nd_cmd->num_records = 0; nd_cmd->address = 0; nd_cmd->length = -1ULL; From 000e0949148382c4962489593a2f05504c2a6771 Mon Sep 17 00:00:00 2001 From: Nishanth Menon Date: Fri, 19 Feb 2016 18:09:51 -0600 Subject: [PATCH 346/489] hwmon: (gpio-fan) Remove un-necessary speed_index lookup for thermal hook Thermal hook gpio_fan_get_cur_state is only interested in knowing the current speed index that was setup in the system, this is already available as part of fan_data->speed_index which is always set by set_fan_speed. Using get_fan_speed_index is useful when we have no idea about the fan speed configuration (for example during fan_ctrl_init). When thermal framework invokes gpio_fan_get_cur_state=>get_fan_speed_index via gpio_fan_get_cur_state especially in a polled configuration for thermal governor, we basically hog the i2c interface to the extent that other functions fail to get any traffic out :(. Instead, just provide the last state set in the driver - since the gpio fan driver is responsible for the fan state immaterial of override, the fan_data->speed_index should accurately reflect the state. Fixes: b5cf88e46bad ("(gpio-fan): Add thermal control hooks") Reported-by: Tony Lindgren Cc: Guenter Roeck Cc: Eduardo Valentin Signed-off-by: Nishanth Menon Cc: stable@vger.kernel.org Signed-off-by: Guenter Roeck --- drivers/hwmon/gpio-fan.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c index 82de3deeb18a..685568b1236d 100644 --- a/drivers/hwmon/gpio-fan.c +++ b/drivers/hwmon/gpio-fan.c @@ -406,16 +406,11 @@ static int gpio_fan_get_cur_state(struct thermal_cooling_device *cdev, unsigned long *state) { struct gpio_fan_data *fan_data = cdev->devdata; - int r; if (!fan_data) return -EINVAL; - r = get_fan_speed_index(fan_data); - if (r < 0) - return r; - - *state = r; + *state = fan_data->speed_index; return 0; } From 035a1539ab63bfdb284bdf6e8459e35897c60564 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 19 Feb 2016 19:43:19 -0500 Subject: [PATCH 347/489] bnxt_en: Poll link at the end of __bnxt_open_nic(). When shutting down the NIC, we shutdown async event processing before freeing all the rings. If there is a link change event during reset, the driver may miss it and the link state may be incorrect after the NIC is re-opened. Poll the link at the end of __bnxt_open_nic() to get the correct link status. Signed-off-by Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 82f4e6d9ac7f..9b560582c7e6 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4662,6 +4662,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) /* Enable TX queues */ bnxt_tx_enable(bp); mod_timer(&bp->timer, jiffies + bp->current_interval); + bnxt_update_link(bp, true); return 0; From de73018fb5474b33dc4f6d6b8d889e40232e325b Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 19 Feb 2016 19:43:20 -0500 Subject: [PATCH 348/489] bnxt_en: Remove unnecessary call to update PHY settings. Fix bnxt_update_phy_setting() to check the correct parameters when determining whether to update the PHY. Requested line speed/duplex should only be checked for forced speed mode. This avoids unnecessary link interruptions when loading the driver. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9b560582c7e6..78f6b5a2b6a0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4554,20 +4554,18 @@ static int bnxt_update_phy_setting(struct bnxt *bp) if (!(link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) && link_info->force_pause_setting != link_info->req_flow_ctrl) update_pause = true; - if (link_info->req_duplex != link_info->duplex_setting) - update_link = true; if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) { if (BNXT_AUTO_MODE(link_info->auto_mode)) update_link = true; if (link_info->req_link_speed != link_info->force_link_speed) update_link = true; + if (link_info->req_duplex != link_info->duplex_setting) + update_link = true; } else { if (link_info->auto_mode == BNXT_LINK_AUTO_NONE) update_link = true; if (link_info->advertising != link_info->auto_link_speeds) update_link = true; - if (link_info->req_link_speed != link_info->auto_link_speed) - update_link = true; } if (update_link) From ba41d46fe03223279054e58d570069fdc62fb768 Mon Sep 17 00:00:00 2001 From: Michael Chan Date: Fri, 19 Feb 2016 19:43:21 -0500 Subject: [PATCH 349/489] bnxt_en: Failure to update PHY is not fatal condition. If we fail to update the PHY, we should print a warning and continue. The current code to exit is buggy as it has not freed up the NIC resources yet. Signed-off-by: Michael Chan Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 78f6b5a2b6a0..8ab000dd52d9 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -4642,7 +4642,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) if (link_re_init) { rc = bnxt_update_phy_setting(bp); if (rc) - goto open_err; + netdev_warn(bp->dev, "failed to update phy settings\n"); } if (irq_re_init) { From b5f0549231ffb025337be5a625b0ff9f52b016f0 Mon Sep 17 00:00:00 2001 From: "Dmitry V. Levin" Date: Fri, 19 Feb 2016 04:27:48 +0300 Subject: [PATCH 350/489] unix_diag: fix incorrect sign extension in unix_lookup_by_ino The value passed by unix_diag_get_exact to unix_lookup_by_ino has type __u32, but unix_lookup_by_ino's argument ino has type int, which is not a problem yet. However, when ino is compared with sock_i_ino return value of type unsigned long, ino is sign extended to signed long, and this results to incorrect comparison on 64-bit architectures for inode numbers greater than INT_MAX. This bug was found by strace test suite. Fixes: 5d3cae8bc39d ("unix_diag: Dumping exact socket core") Signed-off-by: Dmitry V. Levin Acked-by: Cong Wang Signed-off-by: David S. Miller --- net/unix/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/diag.c b/net/unix/diag.c index c512f64d5287..4d9679701a6d 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -220,7 +220,7 @@ done: return skb->len; } -static struct sock *unix_lookup_by_ino(int ino) +static struct sock *unix_lookup_by_ino(unsigned int ino) { int i; struct sock *sk; From 18eceb818dc37bbc783ec7ef7703f270cc6cd281 Mon Sep 17 00:00:00 2001 From: Rainer Weikusat Date: Thu, 18 Feb 2016 12:39:46 +0000 Subject: [PATCH 351/489] af_unix: Don't use continue to re-execute unix_stream_read_generic loop The unix_stream_read_generic function tries to use a continue statement to restart the receive loop after waiting for a message. This may not work as intended as the caller might use a recvmsg call to peek at control messages without specifying a message buffer. If this was the case, the continue will cause the function to return without an error and without the credential information if the function had to wait for a message while it had returned with the credentials otherwise. Change to using goto to restart the loop without checking the condition first in this case so that credentials are returned either way. Signed-off-by: Rainer Weikusat Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/unix/af_unix.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index c51e2831f498..f75f847e688d 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2312,6 +2312,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state) bool drop_skb; struct sk_buff *skb, *last; +redo: unix_state_lock(sk); if (sock_flag(sk, SOCK_DEAD)) { err = -ECONNRESET; @@ -2353,7 +2354,7 @@ again: } mutex_lock(&u->readlock); - continue; + goto redo; unlock: unix_state_unlock(sk); break; From d07c0278da1f4cfc91c3d46d0d07a0d13a949892 Mon Sep 17 00:00:00 2001 From: Jaedon Shin Date: Fri, 19 Feb 2016 13:48:50 +0900 Subject: [PATCH 352/489] net: bcmgenet: Fix internal PHY link state The PHY link state is not chaged in GENETv2 caused by the previous commit 49f7a471e4d1 ("net: bcmgenet: Properly configure PHY to ignore interrupt") was set to PHY_IGNORE_INTERRUPT in bcmgenet_mii_probe(). The internal PHY should use phy_mac_interrupt() when not in use PHY_POLL. The statement for phy_mac_interrupt() has two conditions. The first condition to check GENET_HAS_MDIO_INTR is not related PHY link state, so this patch removes it. Fixes: 49f7a471e4d1 ("net: bcmgenet: Properly configure PHY to ignore interrupt") Signed-off-by: Jaedon Shin Acked-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/genet/bcmgenet.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index b15a60d787c7..d7e01a74e927 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2445,8 +2445,7 @@ static void bcmgenet_irq_task(struct work_struct *work) } /* Link UP/DOWN event */ - if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) && - (priv->irq0_stat & UMAC_IRQ_LINK_EVENT)) { + if (priv->irq0_stat & UMAC_IRQ_LINK_EVENT) { phy_mac_interrupt(priv->phydev, !!(priv->irq0_stat & UMAC_IRQ_LINK_UP)); priv->irq0_stat &= ~UMAC_IRQ_LINK_EVENT; From 2feb55f89096b22e2de066e411a3263647211987 Mon Sep 17 00:00:00 2001 From: Wouter van Kesteren Date: Tue, 16 Feb 2016 22:20:59 +0100 Subject: [PATCH 353/489] fs: allow no_seek_end_llseek to actually seek The user-visible impact of the issue is for example that without this patch sensors-detect breaks when trying to seek in /dev/cpu/0/cpuid. '~0ULL' is a 'unsigned long long' that when converted to a loff_t, which is signed, gets turned into -1. later in vfs_setpos we have 'if (offset > maxsize)', which makes it always return EINVAL. Fixes: b25472f9b961 ("new helpers: no_seek_end_llseek{,_size}()") Signed-off-by: Wouter van Kesteren Reviewed-by: Andreas Dilger Signed-off-by: Al Viro --- fs/read_write.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/fs/read_write.c b/fs/read_write.c index 324ec271cc4e..0c8782aa3d71 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "internal.h" #include @@ -183,7 +184,7 @@ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, - ~0ULL, 0); + OFFSET_MAX, 0); default: return -EINVAL; } From 0e9a7da51b028aee7a72c95096c99fe5ea2a01f0 Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Thu, 4 Feb 2016 02:56:30 +0100 Subject: [PATCH 354/489] xattr handlers: plug a lock leak in simple_xattr_list The code could leak xattrs->lock on error. Problem introduced with 786534b92f3ce68f4 "tmpfs: listxattr should include POSIX ACL xattrs". Signed-off-by: Mateusz Guzik Signed-off-by: Al Viro --- fs/xattr.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/fs/xattr.c b/fs/xattr.c index 07d0e47f6a7f..4861322e28e8 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -940,7 +940,7 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, bool trusted = capable(CAP_SYS_ADMIN); struct simple_xattr *xattr; ssize_t remaining_size = size; - int err; + int err = 0; #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl) { @@ -965,11 +965,11 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) - return err; + break; } spin_unlock(&xattrs->lock); - return size - remaining_size; + return err ? err : size - remaining_size; } /* From 0bacbe528e26422e424d110ebda4ec68ea0fd5eb Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 2 Feb 2016 02:28:05 +0000 Subject: [PATCH 355/489] affs_do_readpage_ofs(): just use kmap_atomic() around memcpy() It forgets kunmap() on a failure exit, but there's really no point keeping the page kmapped at all - after all, what we are doing is a bunch of memcpy() into the parts of page, so kmap_atomic()/kunmap_atomic() just around those memcpy() is enough. Spotted-by: Insu Yun Signed-off-by: Al Viro --- fs/affs/file.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/fs/affs/file.c b/fs/affs/file.c index 0548c53f41d5..22fc7c802d69 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -511,8 +511,6 @@ affs_do_readpage_ofs(struct page *page, unsigned to) pr_debug("%s(%lu, %ld, 0, %d)\n", __func__, inode->i_ino, page->index, to); BUG_ON(to > PAGE_CACHE_SIZE); - kmap(page); - data = page_address(page); bsize = AFFS_SB(sb)->s_data_blksize; tmp = page->index << PAGE_CACHE_SHIFT; bidx = tmp / bsize; @@ -524,14 +522,15 @@ affs_do_readpage_ofs(struct page *page, unsigned to) return PTR_ERR(bh); tmp = min(bsize - boff, to - pos); BUG_ON(pos + tmp > to || tmp > bsize); + data = kmap_atomic(page); memcpy(data + pos, AFFS_DATA(bh) + boff, tmp); + kunmap_atomic(data); affs_brelse(bh); bidx++; pos += tmp; boff = 0; } flush_dcache_page(page); - kunmap(page); return 0; } From 7ae8fd0351f912b075149a1e03a017be8b903b9a Mon Sep 17 00:00:00 2001 From: Maxim Patlasov Date: Tue, 16 Feb 2016 11:45:33 -0800 Subject: [PATCH 356/489] fs/pnode.c: treat zero mnt_group_id-s as unequal propagate_one(m) calculates "type" argument for copy_tree() like this: > if (m->mnt_group_id == last_dest->mnt_group_id) { > type = CL_MAKE_SHARED; > } else { > type = CL_SLAVE; > if (IS_MNT_SHARED(m)) > type |= CL_MAKE_SHARED; > } The "type" argument then governs clone_mnt() behavior with respect to flags and mnt_master of new mount. When we iterate through a slave group, it is possible that both current "m" and "last_dest" are not shared (although, both are slaves, i.e. have non-NULL mnt_master-s). Then the comparison above erroneously makes new mount shared and sets its mnt_master to last_source->mnt_master. The patch fixes the problem by handling zero mnt_group_id-s as though they are unequal. The similar problem exists in the implementation of "else" clause above when we have to ascend upward in the master/slave tree by calling: > last_source = last_source->mnt_master; > last_dest = last_source->mnt_parent; proper number of times. The last step is governed by "n->mnt_group_id != last_dest->mnt_group_id" condition that may lie if both are zero. The patch fixes this case in the same way as the former one. [AV: don't open-code an obvious helper...] Signed-off-by: Maxim Patlasov Signed-off-by: Al Viro --- fs/pnode.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/fs/pnode.c b/fs/pnode.c index 6367e1e435c6..c524fdddc7fb 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -202,6 +202,11 @@ static struct mount *last_dest, *last_source, *dest_master; static struct mountpoint *mp; static struct hlist_head *list; +static inline bool peers(struct mount *m1, struct mount *m2) +{ + return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; +} + static int propagate_one(struct mount *m) { struct mount *child; @@ -212,7 +217,7 @@ static int propagate_one(struct mount *m) /* skip if mountpoint isn't covered by it */ if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) return 0; - if (m->mnt_group_id == last_dest->mnt_group_id) { + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { struct mount *n, *p; @@ -223,7 +228,7 @@ static int propagate_one(struct mount *m) last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } - if (n->mnt_group_id != last_dest->mnt_group_id) { + if (!peers(n, last_dest)) { last_source = last_source->mnt_master; last_dest = last_source->mnt_parent; } From 3bd7594e69bd97c962faa6a5ae15dd8c6c082636 Mon Sep 17 00:00:00 2001 From: Douglas Anderson Date: Fri, 19 Feb 2016 14:25:21 -0800 Subject: [PATCH 357/489] Bluetooth: hci_core: Avoid mixing up req_complete and req_complete_skb In commit 44d271377479 ("Bluetooth: Compress the size of struct hci_ctrl") we squashed down the size of the structure by using a union with the assumption that all users would use the flag to determine whether we had a req_complete or a req_complete_skb. Unfortunately we had a case in hci_req_cmd_complete() where we weren't looking at the flag. This can result in a situation where we might be storing a hci_req_complete_skb_t in a hci_req_complete_t variable, or vice versa. During some testing I found at least one case where the function hci_req_sync_complete() was called improperly because the kernel thought that it didn't require an SKB. Looking through the stack in kgdb I found that it was called by hci_event_packet() and that hci_event_packet() had both of its locals "req_complete" and "req_complete_skb" pointing to the same place: both to hci_req_sync_complete(). Let's make sure we always check the flag. For more details on debugging done, see . Fixes: 44d271377479 ("Bluetooth: Compress the size of struct hci_ctrl") Signed-off-by: Douglas Anderson Acked-by: Johan Hedberg Signed-off-by: Marcel Holtmann --- net/bluetooth/hci_core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 47bcef754796..883c821a9e78 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -4112,8 +4112,10 @@ void hci_req_cmd_complete(struct hci_dev *hdev, u16 opcode, u8 status, break; } - *req_complete = bt_cb(skb)->hci.req_complete; - *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; + if (bt_cb(skb)->hci.req_flags & HCI_REQ_SKB) + *req_complete_skb = bt_cb(skb)->hci.req_complete_skb; + else + *req_complete = bt_cb(skb)->hci.req_complete; kfree_skb(skb); } spin_unlock_irqrestore(&hdev->cmd_q.lock, flags); From 59ceeaaf355fa0fb16558ef7c24413c804932ada Mon Sep 17 00:00:00 2001 From: Simon Guinot Date: Thu, 10 Sep 2015 00:15:18 +0200 Subject: [PATCH 358/489] kernel/resource.c: fix muxed resource handling in __request_region() In __request_region, if a conflict with a BUSY and MUXED resource is detected, then the caller goes to sleep and waits for the resource to be released. A pointer on the conflicting resource is kept. At wake-up this pointer is used as a parent to retry to request the region. A first problem is that this pointer might well be invalid (if for example the conflicting resource have already been freed). Another problem is that the next call to __request_region() fails to detect a remaining conflict. The previously conflicting resource is passed as a parameter and __request_region() will look for a conflict among the children of this resource and not at the resource itself. It is likely to succeed anyway, even if there is still a conflict. Instead, the parent of the conflicting resource should be passed to __request_region(). As a fix, this patch doesn't update the parent resource pointer in the case we have to wait for a muxed region right after. Reported-and-tested-by: Vincent Pelletier Signed-off-by: Simon Guinot Tested-by: Vincent Donnefort Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- kernel/resource.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/resource.c b/kernel/resource.c index 09c0597840b0..3669d1bfc425 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -1083,9 +1083,10 @@ struct resource * __request_region(struct resource *parent, if (!conflict) break; if (conflict != parent) { - parent = conflict; - if (!(conflict->flags & IORESOURCE_BUSY)) + if (!(conflict->flags & IORESOURCE_BUSY)) { + parent = conflict; continue; + } } if (conflict->flags & flags & IORESOURCE_MUXED) { add_wait_queue(&muxed_resource_wait, &wait); From 81f70ba233d5f660e1ea5fe23260ee323af5d53a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 20 Feb 2016 13:39:35 -0800 Subject: [PATCH 359/489] Linux 4.5-rc5 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index 701c36056ca8..fbe1b921798f 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc4 +EXTRAVERSION = -rc5 NAME = Blurry Fish Butt # *DOCUMENTATION* From e5bdfd50d6f76077bf8441d130c606229e100d40 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Sat, 20 Feb 2016 14:19:34 -0800 Subject: [PATCH 360/489] Revert "usb: hub: do not clear BOS field during reset device" This reverts commit d8f00cd685f5c8e0def8593e520a7fef12c22407. Tony writes: This upstream commit is causing an oops: d8f00cd685f5 ("usb: hub: do not clear BOS field during reset device") This patch has already been included in several -stable kernels. Here are the affected kernels: 4.5.0-rc4 (current git) 4.4.2 4.3.6 (currently in review) 4.1.18 3.18.27 3.14.61 How to reproduce the problem: Boot kernel with slub debugging enabled (otherwise memory corruption will cause random oopses later instead of immediately) Plug in USB 3.0 disk to xhci USB 3.0 port dd if=/dev/sdc of=/dev/null bs=65536 (where /dev/sdc is the USB 3.0 disk) Unplug USB cable while dd is still going Oops is immediate: Reported-by: Tony Battersby Cc: Du, Changbin Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 350dcd9af5d8..51b436918f78 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -5401,6 +5401,7 @@ static int usb_reset_and_verify_device(struct usb_device *udev) } bos = udev->bos; + udev->bos = NULL; for (i = 0; i < SET_CONFIG_TRIES; ++i) { @@ -5493,11 +5494,8 @@ done: usb_set_usb2_hardware_lpm(udev, 1); usb_unlocked_enable_lpm(udev); usb_enable_ltm(udev); - /* release the new BOS descriptor allocated by hub_port_init() */ - if (udev->bos != bos) { - usb_release_bos_descriptor(udev); - udev->bos = bos; - } + usb_release_bos_descriptor(udev); + udev->bos = bos; return 0; re_enumerate: From 7a64cd887fdb97f074c3fda03bee0bfb9faceac3 Mon Sep 17 00:00:00 2001 From: Lisa Du Date: Wed, 17 Feb 2016 09:32:52 +0800 Subject: [PATCH 361/489] drivers: android: correct the size of struct binder_uintptr_t for BC_DEAD_BINDER_DONE There's one point was missed in the patch commit da49889deb34 ("staging: binder: Support concurrent 32 bit and 64 bit processes."). When configure BINDER_IPC_32BIT, the size of binder_uintptr_t was 32bits, but size of void * is 64bit on 64bit system. Correct it here. Signed-off-by: Lisa Du Signed-off-by: Nicolas Boichat Fixes: da49889deb34 ("staging: binder: Support concurrent 32 bit and 64 bit processes.") Cc: Acked-by: Olof Johansson Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/android/binder.c b/drivers/android/binder.c index a39e85f9efa9..7d00b7a015ea 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2074,7 +2074,7 @@ static int binder_thread_write(struct binder_proc *proc, if (get_user(cookie, (binder_uintptr_t __user *)ptr)) return -EFAULT; - ptr += sizeof(void *); + ptr += sizeof(cookie); list_for_each_entry(w, &proc->delivered_death, entry) { struct binder_ref_death *tmp_death = container_of(w, struct binder_ref_death, work); From 90cfde46586d2286488d8ed636929e936c0c9ab2 Mon Sep 17 00:00:00 2001 From: Gerhard Uttenthaler Date: Tue, 22 Dec 2015 17:29:16 +0100 Subject: [PATCH 362/489] can: ems_usb: Fix possible tx overflow This patch fixes the problem that more CAN messages could be sent to the interface as could be send on the CAN bus. This was more likely for slow baud rates. The sleeping _start_xmit was woken up in the _write_bulk_callback. Under heavy TX load this produced another bulk transfer without checking the free_slots variable and hence caused the overflow in the interface. Signed-off-by: Gerhard Uttenthaler Cc: linux-stable Signed-off-by: Marc Kleine-Budde --- drivers/net/can/usb/ems_usb.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index fc5b75675cd8..eb7192fab593 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -117,6 +117,9 @@ MODULE_LICENSE("GPL v2"); */ #define EMS_USB_ARM7_CLOCK 8000000 +#define CPC_TX_QUEUE_TRIGGER_LOW 25 +#define CPC_TX_QUEUE_TRIGGER_HIGH 35 + /* * CAN-Message representation in a CPC_MSG. Message object type is * CPC_MSG_TYPE_CAN_FRAME or CPC_MSG_TYPE_RTR_FRAME or @@ -278,6 +281,11 @@ static void ems_usb_read_interrupt_callback(struct urb *urb) switch (urb->status) { case 0: dev->free_slots = dev->intr_in_buffer[1]; + if(dev->free_slots > CPC_TX_QUEUE_TRIGGER_HIGH){ + if (netif_queue_stopped(netdev)){ + netif_wake_queue(netdev); + } + } break; case -ECONNRESET: /* unlink */ @@ -526,8 +534,6 @@ static void ems_usb_write_bulk_callback(struct urb *urb) /* Release context */ context->echo_index = MAX_TX_URBS; - if (netif_queue_stopped(netdev)) - netif_wake_queue(netdev); } /* @@ -587,7 +593,7 @@ static int ems_usb_start(struct ems_usb *dev) int err, i; dev->intr_in_buffer[0] = 0; - dev->free_slots = 15; /* initial size */ + dev->free_slots = 50; /* initial size */ for (i = 0; i < MAX_RX_URBS; i++) { struct urb *urb = NULL; @@ -835,7 +841,7 @@ static netdev_tx_t ems_usb_start_xmit(struct sk_buff *skb, struct net_device *ne /* Slow down tx path */ if (atomic_read(&dev->active_tx_urbs) >= MAX_TX_URBS || - dev->free_slots < 5) { + dev->free_slots < CPC_TX_QUEUE_TRIGGER_LOW) { netif_stop_queue(netdev); } } From e35a49b163fa2108cf82c6f07a3fbe371e468878 Mon Sep 17 00:00:00 2001 From: Sebastian Reichel Date: Sun, 17 Jan 2016 21:36:03 +0100 Subject: [PATCH 363/489] MAINTAINERS: update bq27xxx driver MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Update reviewers for bq27xxx, so that Pali and Andrew are reviewers with status and maintainer inherited from the power supply subsystem entry. Signed-off-by: Sebastian Reichel Acked-by: Pali Rohár Acked-by: Andrew F. Davis --- MAINTAINERS | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4978dc19a4d2..116a448ae77e 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7686,13 +7686,13 @@ S: Maintained F: arch/nios2/ NOKIA N900 POWER SUPPLY DRIVERS -M: Pali Rohár -S: Maintained +R: Pali Rohár F: include/linux/power/bq2415x_charger.h F: include/linux/power/bq27xxx_battery.h F: include/linux/power/isp1704_charger.h F: drivers/power/bq2415x_charger.c F: drivers/power/bq27xxx_battery.c +F: drivers/power/bq27xxx_battery_i2c.c F: drivers/power/isp1704_charger.c F: drivers/power/rx51_battery.c @@ -9558,6 +9558,12 @@ M: Andreas Noever S: Maintained F: drivers/thunderbolt/ +TI BQ27XXX POWER SUPPLY DRIVER +R: Andrew F. Davis +F: include/linux/power/bq27xxx_battery.h +F: drivers/power/bq27xxx_battery.c +F: drivers/power/bq27xxx_battery_i2c.c + TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER M: John Stultz M: Thomas Gleixner From 9aafabc7fece13c8e2a1f680908c73ee19f0f79b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Tue, 2 Feb 2016 14:47:37 +0200 Subject: [PATCH 364/489] power: bq27xxx_battery: Restore device name MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch <703df6c09795> ("power: bq27xxx_battery: Reorganize I2C into a module") has removed the device name numbering from bq27xxx_battery_i2c_probe. Fix that by restoring the code. Fixes: 703df6c097956d17a818e63961c82e8e9eef9fef Signed-off-by: Ivaylo Dimitrov Reviewed-by: Pali Rohár Tested-by: Pali Rohár Signed-off-by: Sebastian Reichel --- drivers/power/bq27xxx_battery_i2c.c | 37 ++++++++++++++++++++++++--- include/linux/power/bq27xxx_battery.h | 1 + 2 files changed, 35 insertions(+), 3 deletions(-) diff --git a/drivers/power/bq27xxx_battery_i2c.c b/drivers/power/bq27xxx_battery_i2c.c index 9429e66be096..8eafc6f0df88 100644 --- a/drivers/power/bq27xxx_battery_i2c.c +++ b/drivers/power/bq27xxx_battery_i2c.c @@ -21,6 +21,9 @@ #include +static DEFINE_IDR(battery_id); +static DEFINE_MUTEX(battery_mutex); + static irqreturn_t bq27xxx_battery_irq_handler_thread(int irq, void *data) { struct bq27xxx_device_info *di = data; @@ -70,19 +73,33 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client, { struct bq27xxx_device_info *di; int ret; + char *name; + int num; + + /* Get new ID for the new battery device */ + mutex_lock(&battery_mutex); + num = idr_alloc(&battery_id, client, 0, 0, GFP_KERNEL); + mutex_unlock(&battery_mutex); + if (num < 0) + return num; + + name = devm_kasprintf(&client->dev, GFP_KERNEL, "%s-%d", id->name, num); + if (!name) + goto err_mem; di = devm_kzalloc(&client->dev, sizeof(*di), GFP_KERNEL); if (!di) - return -ENOMEM; + goto err_mem; + di->id = num; di->dev = &client->dev; di->chip = id->driver_data; - di->name = id->name; + di->name = name; di->bus.read = bq27xxx_battery_i2c_read; ret = bq27xxx_battery_setup(di); if (ret) - return ret; + goto err_failed; /* Schedule a polling after about 1 min */ schedule_delayed_work(&di->work, 60 * HZ); @@ -103,6 +120,16 @@ static int bq27xxx_battery_i2c_probe(struct i2c_client *client, } return 0; + +err_mem: + ret = -ENOMEM; + +err_failed: + mutex_lock(&battery_mutex); + idr_remove(&battery_id, num); + mutex_unlock(&battery_mutex); + + return ret; } static int bq27xxx_battery_i2c_remove(struct i2c_client *client) @@ -111,6 +138,10 @@ static int bq27xxx_battery_i2c_remove(struct i2c_client *client) bq27xxx_battery_teardown(di); + mutex_lock(&battery_mutex); + idr_remove(&battery_id, di->id); + mutex_unlock(&battery_mutex); + return 0; } diff --git a/include/linux/power/bq27xxx_battery.h b/include/linux/power/bq27xxx_battery.h index 998d8f1c3c91..b50c0492629d 100644 --- a/include/linux/power/bq27xxx_battery.h +++ b/include/linux/power/bq27xxx_battery.h @@ -49,6 +49,7 @@ struct bq27xxx_reg_cache { struct bq27xxx_device_info { struct device *dev; + int id; enum bq27xxx_chip chip; const char *name; struct bq27xxx_access_methods bus; From 4328daa2e79ed904a42ce00a9f38b9c36b44b21a Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Sun, 21 Feb 2016 19:09:22 -0500 Subject: [PATCH 365/489] dm: fix dm_rq_target_io leak on faults with .request_fn DM w/ blk-mq paths Using request-based DM mpath configured with the following stacking (.request_fn DM mpath ontop of scsi-mq paths): echo Y > /sys/module/scsi_mod/parameters/use_blk_mq echo N > /sys/module/dm_mod/parameters/use_blk_mq 'struct dm_rq_target_io' would leak if a request is requeued before a blk-mq clone is allocated (or fails to allocate). free_rq_tio() wasn't being called. kmemleak reported: unreferenced object 0xffff8800b90b98c0 (size 112): comm "kworker/7:1H", pid 5692, jiffies 4295056109 (age 78.589s) hex dump (first 32 bytes): 00 d0 5c 2c 03 88 ff ff 40 00 bf 01 00 c9 ff ff ..\,....@....... e0 d9 b1 34 00 88 ff ff 00 00 00 00 00 00 00 00 ...4............ backtrace: [] kmemleak_alloc+0x4e/0xb0 [] kmem_cache_alloc+0xc3/0x1e0 [] mempool_alloc_slab+0x15/0x20 [] mempool_alloc+0x6e/0x170 [] dm_old_prep_fn+0x3c/0x180 [dm_mod] [] blk_peek_request+0x168/0x290 [] dm_request_fn+0xb2/0x1b0 [dm_mod] [] __blk_run_queue+0x33/0x40 [] blk_delay_work+0x25/0x40 [] process_one_work+0x14f/0x3d0 [] worker_thread+0x125/0x4b0 [] kthread+0xd8/0xf0 [] ret_from_fork+0x3f/0x70 [] 0xffffffffffffffff crash> struct -o dm_rq_target_io struct dm_rq_target_io { ... } SIZE: 112 Fixes: e5863d9ad7 ("dm: allocate requests in target when stacking on blk-mq devices") Cc: stable@vger.kernel.org # 4.0+ Signed-off-by: Mike Snitzer --- drivers/md/dm.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 5df40480228b..dd834927bc66 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1191,6 +1191,8 @@ static void dm_unprep_request(struct request *rq) if (clone) free_rq_clone(clone); + else if (!tio->md->queue->mq_ops) + free_rq_tio(tio); } /* From d9749fb5942f51555dc9ce1ac0dbb1806960a975 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Thu, 18 Feb 2016 16:10:57 -0500 Subject: [PATCH 366/489] sctp: Fix port hash table size computation Dmitry Vyukov noted recently that the sctp_port_hashtable had an error in its size computation, observing that the current method never guaranteed that the hashsize (measured in number of entries) would be a power of two, which the input hash function for that table requires. The root cause of the problem is that two values need to be computed (one, the allocation order of the storage requries, as passed to __get_free_pages, and two the number of entries for the hash table). Both need to be ^2, but for different reasons, and the existing code is simply computing one order value, and using it as the basis for both, which is wrong (i.e. it assumes that ((1< Reported-by: Dmitry Vyukov CC: Dmitry Vyukov CC: Vladislav Yasevich CC: "David S. Miller" Signed-off-by: David S. Miller --- net/sctp/protocol.c | 46 +++++++++++++++++++++++++++++++++++++-------- 1 file changed, 38 insertions(+), 8 deletions(-) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index ab0d538a74ed..1099e99a53c4 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -60,6 +60,8 @@ #include #include +#define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024) + /* Global data structures. */ struct sctp_globals sctp_globals __read_mostly; @@ -1355,6 +1357,8 @@ static __init int sctp_init(void) unsigned long limit; int max_share; int order; + int num_entries; + int max_entry_order; sock_skb_cb_check_size(sizeof(struct sctp_ulpevent)); @@ -1407,14 +1411,24 @@ static __init int sctp_init(void) /* Size and allocate the association hash table. * The methodology is similar to that of the tcp hash tables. + * Though not identical. Start by getting a goal size */ if (totalram_pages >= (128 * 1024)) goal = totalram_pages >> (22 - PAGE_SHIFT); else goal = totalram_pages >> (24 - PAGE_SHIFT); - for (order = 0; (1UL << order) < goal; order++) - ; + /* Then compute the page order for said goal */ + order = get_order(goal); + + /* Now compute the required page order for the maximum sized table we + * want to create + */ + max_entry_order = get_order(MAX_SCTP_PORT_HASH_ENTRIES * + sizeof(struct sctp_bind_hashbucket)); + + /* Limit the page order by that maximum hash table size */ + order = min(order, max_entry_order); /* Allocate and initialize the endpoint hash table. */ sctp_ep_hashsize = 64; @@ -1430,20 +1444,35 @@ static __init int sctp_init(void) INIT_HLIST_HEAD(&sctp_ep_hashtable[i].chain); } - /* Allocate and initialize the SCTP port hash table. */ + /* Allocate and initialize the SCTP port hash table. + * Note that order is initalized to start at the max sized + * table we want to support. If we can't get that many pages + * reduce the order and try again + */ do { - sctp_port_hashsize = (1UL << order) * PAGE_SIZE / - sizeof(struct sctp_bind_hashbucket); - if ((sctp_port_hashsize > (64 * 1024)) && order > 0) - continue; sctp_port_hashtable = (struct sctp_bind_hashbucket *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN, order); } while (!sctp_port_hashtable && --order > 0); + if (!sctp_port_hashtable) { pr_err("Failed bind hash alloc\n"); status = -ENOMEM; goto err_bhash_alloc; } + + /* Now compute the number of entries that will fit in the + * port hash space we allocated + */ + num_entries = (1UL << order) * PAGE_SIZE / + sizeof(struct sctp_bind_hashbucket); + + /* And finish by rounding it down to the nearest power of two + * this wastes some memory of course, but its needed because + * the hash function operates based on the assumption that + * that the number of entries is a power of two + */ + sctp_port_hashsize = rounddown_pow_of_two(num_entries); + for (i = 0; i < sctp_port_hashsize; i++) { spin_lock_init(&sctp_port_hashtable[i].lock); INIT_HLIST_HEAD(&sctp_port_hashtable[i].chain); @@ -1452,7 +1481,8 @@ static __init int sctp_init(void) if (sctp_transport_hashtable_init()) goto err_thash_alloc; - pr_info("Hash tables configured (bind %d)\n", sctp_port_hashsize); + pr_info("Hash tables configured (bind %d/%d)\n", sctp_port_hashsize, + num_entries); sctp_sysctl_register(); From 3301be32d4ba95136ff52fb0aee2bdb6077f40b1 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Fri, 19 Feb 2016 11:44:51 +0000 Subject: [PATCH 367/489] MAINTAINERS: Drop myself as xen netback maintainer Wei has been picking this up for quite a while now. Signed-off-by: Ian Campbell Cc: Wei Liu Acked-by: Wei Liu Signed-off-by: David S. Miller --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 4f55edf0a589..19ee99fc7e24 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12021,7 +12021,6 @@ F: arch/arm64/xen/ F: arch/arm64/include/asm/xen/ XEN NETWORK BACKEND DRIVER -M: Ian Campbell M: Wei Liu L: xen-devel@lists.xenproject.org (moderated for non-subscribers) L: netdev@vger.kernel.org From 9ecfe875c4f311618cc918aded716017dcd2ddf1 Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Fri, 19 Feb 2016 12:58:42 -0500 Subject: [PATCH 368/489] net: ti: netcp: restore get/set_pad_info() functionality The commit 899077791403 ("netcp: try to reduce type confusion in descriptors") introduces a regression in Kernel 4.5-rc1 and it breaks get/set_pad_info() functionality. The TI NETCP driver uses pad0 and pad1 fields of knav_dma_desc to store DMA/MEM buffer pointer and buffer size respectively. And in both cases for Keystone 2 the pointer type size is 32 bit regardless of LAPE enabled or not, because CONFIG_ARCH_DMA_ADDR_T_64BIT originally is not expected to be defined. Unfortunately, above commit changed buffer's pointers save/restore code (get/set_pad_info()) and added intermediate conversation to u64 which works incorrectly on 32bit Keystone 2 and causes TI NETCP driver crash in RX/TX path due to "Unable to handle kernel NULL pointer" exception. This issue was reported and discussed in [1]. Hence, fix it by partially reverting above commit and restoring get/set_pad_info() functionality as it was before. [1] https://www.mail-archive.com/netdev@vger.kernel.org/msg95361.html Cc: Wingman Kwok Cc: Mugunthan V N CC: David Laight CC: Arnd Bergmann Reported-by: Franklin S Cooper Jr Signed-off-by: Grygorii Strashko Signed-off-by: Murali Karicheri Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_core.c | 59 +++++++++------------------- 1 file changed, 18 insertions(+), 41 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index c61d66d38634..0b26e5209413 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -117,20 +117,10 @@ static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc, *ndesc = le32_to_cpu(desc->next_desc); } -static void get_pad_info(u32 *pad0, u32 *pad1, u32 *pad2, struct knav_dma_desc *desc) +static void get_pad_info(u32 *pad0, u32 *pad1, struct knav_dma_desc *desc) { *pad0 = le32_to_cpu(desc->pad[0]); *pad1 = le32_to_cpu(desc->pad[1]); - *pad2 = le32_to_cpu(desc->pad[2]); -} - -static void get_pad_ptr(void **padptr, struct knav_dma_desc *desc) -{ - u64 pad64; - - pad64 = le32_to_cpu(desc->pad[0]) + - ((u64)le32_to_cpu(desc->pad[1]) << 32); - *padptr = (void *)(uintptr_t)pad64; } static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len, @@ -163,11 +153,10 @@ static void set_desc_info(u32 desc_info, u32 pkt_info, desc->packet_info = cpu_to_le32(pkt_info); } -static void set_pad_info(u32 pad0, u32 pad1, u32 pad2, struct knav_dma_desc *desc) +static void set_pad_info(u32 pad0, u32 pad1, struct knav_dma_desc *desc) { desc->pad[0] = cpu_to_le32(pad0); desc->pad[1] = cpu_to_le32(pad1); - desc->pad[2] = cpu_to_le32(pad1); } static void set_org_pkt_info(dma_addr_t buff, u32 buff_len, @@ -581,7 +570,6 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, dma_addr_t dma_desc, dma_buf; unsigned int buf_len, dma_sz = sizeof(*ndesc); void *buf_ptr; - u32 pad[2]; u32 tmp; get_words(&dma_desc, 1, &desc->next_desc); @@ -593,14 +581,12 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, break; } get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc); - get_pad_ptr(&buf_ptr, ndesc); + get_pad_info((u32 *)&buf_ptr, &buf_len, ndesc); dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE); __free_page(buf_ptr); knav_pool_desc_put(netcp->rx_pool, desc); } - - get_pad_info(&pad[0], &pad[1], &buf_len, desc); - buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32)); + get_pad_info((u32 *)&buf_ptr, &buf_len, desc); if (buf_ptr) netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr); @@ -639,8 +625,8 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) dma_addr_t dma_desc, dma_buff; struct netcp_packet p_info; struct sk_buff *skb; - u32 pad[2]; void *org_buf_ptr; + u32 tmp; dma_desc = knav_queue_pop(netcp->rx_queue, &dma_sz); if (!dma_desc) @@ -653,8 +639,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc); - get_pad_info(&pad[0], &pad[1], &org_buf_len, desc); - org_buf_ptr = (void *)(uintptr_t)(pad[0] + ((u64)pad[1] << 32)); + get_pad_info((u32 *)&org_buf_ptr, &org_buf_len, desc); if (unlikely(!org_buf_ptr)) { dev_err(netcp->ndev_dev, "NULL bufptr in desc\n"); @@ -679,7 +664,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) /* Fill in the page fragment list */ while (dma_desc) { struct page *page; - void *ptr; ndesc = knav_pool_desc_unmap(netcp->rx_pool, dma_desc, dma_sz); if (unlikely(!ndesc)) { @@ -688,8 +672,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc); - get_pad_ptr(&ptr, ndesc); - page = ptr; + get_pad_info((u32 *)&page, &tmp, ndesc); if (likely(dma_buff && buf_len && page)) { dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE, @@ -767,6 +750,7 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) unsigned int buf_len, dma_sz; dma_addr_t dma; void *buf_ptr; + u32 tmp; /* Allocate descriptor */ while ((dma = knav_queue_pop(netcp->rx_fdq[fdq], &dma_sz))) { @@ -777,7 +761,7 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) } get_org_pkt_info(&dma, &buf_len, desc); - get_pad_ptr(&buf_ptr, desc); + get_pad_info((u32 *)&buf_ptr, &tmp, desc); if (unlikely(!dma)) { dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n"); @@ -829,7 +813,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) struct page *page; dma_addr_t dma; void *bufptr; - u32 pad[3]; + u32 pad[2]; /* Allocate descriptor */ hwdesc = knav_pool_desc_get(netcp->rx_pool); @@ -846,7 +830,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); bufptr = netdev_alloc_frag(primary_buf_len); - pad[2] = primary_buf_len; + pad[1] = primary_buf_len; if (unlikely(!bufptr)) { dev_warn_ratelimited(netcp->ndev_dev, @@ -858,9 +842,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (unlikely(dma_mapping_error(netcp->dev, dma))) goto fail; - pad[0] = lower_32_bits((uintptr_t)bufptr); - pad[1] = upper_32_bits((uintptr_t)bufptr); - + pad[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD); @@ -870,9 +852,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) } buf_len = PAGE_SIZE; dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE); - pad[0] = lower_32_bits(dma); - pad[1] = upper_32_bits(dma); - pad[2] = 0; + pad[0] = (u32)page; + pad[1] = 0; } desc_info = KNAV_DMA_DESC_PS_INFO_IN_DESC; @@ -882,7 +863,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) << KNAV_DMA_DESC_RETQ_SHIFT; set_org_pkt_info(dma, buf_len, hwdesc); - set_pad_info(pad[0], pad[1], pad[2], hwdesc); + set_pad_info(pad[0], pad[1], hwdesc); set_desc_info(desc_info, pkt_info, hwdesc); /* Push to FDQs */ @@ -971,11 +952,11 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, unsigned int budget) { struct knav_dma_desc *desc; - void *ptr; struct sk_buff *skb; unsigned int dma_sz; dma_addr_t dma; int pkts = 0; + u32 tmp; while (budget--) { dma = knav_queue_pop(netcp->tx_compl_q, &dma_sz); @@ -988,8 +969,7 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, continue; } - get_pad_ptr(&ptr, desc); - skb = ptr; + get_pad_info((u32 *)&skb, &tmp, desc); netcp_free_tx_desc_chain(netcp, desc, dma_sz); if (!skb) { dev_err(netcp->ndev_dev, "No skb in Tx desc\n"); @@ -1194,10 +1174,7 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, } set_words(&tmp, 1, &desc->packet_info); - tmp = lower_32_bits((uintptr_t)&skb); - set_words(&tmp, 1, &desc->pad[0]); - tmp = upper_32_bits((uintptr_t)&skb); - set_words(&tmp, 1, &desc->pad[1]); + set_words((u32 *)&skb, 1, &desc->pad[0]); if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) { tmp = tx_pipe->switch_to_port; From b1cb86ae0e5951e9747ec7a5b33d1c1217791b75 Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Fri, 19 Feb 2016 12:58:43 -0500 Subject: [PATCH 369/489] soc: ti: knav_dma: rename pad in struct knav_dma_desc to sw_data Rename the pad to sw_data as per description of this field in the hardware spec(refer sprugr9 from www.ti.com). Latest version of the document is at http://www.ti.com/lit/ug/sprugr9h/sprugr9h.pdf and section 3.1 Host Packet Descriptor describes this field. Define and use a constant for the size of sw_data field similar to other fields in the struct for desc and document the sw_data field in the header. As the sw_data is not touched by hw, it's type can be changed to u32. Rename the helpers to match with the updated dma desc field sw_data. Cc: Wingman Kwok Cc: Mugunthan V N CC: Arnd Bergmann CC: Grygorii Strashko CC: David Laight Signed-off-by: Murali Karicheri Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_core.c | 40 +++++++++++++++------------- include/linux/soc/ti/knav_dma.h | 4 ++- 2 files changed, 24 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 0b26e5209413..84bab29995fd 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -117,10 +117,11 @@ static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc, *ndesc = le32_to_cpu(desc->next_desc); } -static void get_pad_info(u32 *pad0, u32 *pad1, struct knav_dma_desc *desc) +static void get_sw_data(u32 *data0, u32 *data1, struct knav_dma_desc *desc) { - *pad0 = le32_to_cpu(desc->pad[0]); - *pad1 = le32_to_cpu(desc->pad[1]); + /* No Endian conversion needed as this data is untouched by hw */ + *data0 = desc->sw_data[0]; + *data1 = desc->sw_data[1]; } static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len, @@ -153,10 +154,11 @@ static void set_desc_info(u32 desc_info, u32 pkt_info, desc->packet_info = cpu_to_le32(pkt_info); } -static void set_pad_info(u32 pad0, u32 pad1, struct knav_dma_desc *desc) +static void set_sw_data(u32 data0, u32 data1, struct knav_dma_desc *desc) { - desc->pad[0] = cpu_to_le32(pad0); - desc->pad[1] = cpu_to_le32(pad1); + /* No Endian conversion needed as this data is untouched by hw */ + desc->sw_data[0] = data0; + desc->sw_data[1] = data1; } static void set_org_pkt_info(dma_addr_t buff, u32 buff_len, @@ -581,12 +583,12 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, break; } get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc); - get_pad_info((u32 *)&buf_ptr, &buf_len, ndesc); + get_sw_data((u32 *)&buf_ptr, &buf_len, ndesc); dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE); __free_page(buf_ptr); knav_pool_desc_put(netcp->rx_pool, desc); } - get_pad_info((u32 *)&buf_ptr, &buf_len, desc); + get_sw_data((u32 *)&buf_ptr, &buf_len, desc); if (buf_ptr) netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr); @@ -639,7 +641,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc); - get_pad_info((u32 *)&org_buf_ptr, &org_buf_len, desc); + get_sw_data((u32 *)&org_buf_ptr, &org_buf_len, desc); if (unlikely(!org_buf_ptr)) { dev_err(netcp->ndev_dev, "NULL bufptr in desc\n"); @@ -672,7 +674,7 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc); - get_pad_info((u32 *)&page, &tmp, ndesc); + get_sw_data((u32 *)&page, &tmp, ndesc); if (likely(dma_buff && buf_len && page)) { dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE, @@ -761,7 +763,7 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) } get_org_pkt_info(&dma, &buf_len, desc); - get_pad_info((u32 *)&buf_ptr, &tmp, desc); + get_sw_data((u32 *)&buf_ptr, &tmp, desc); if (unlikely(!dma)) { dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n"); @@ -813,7 +815,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) struct page *page; dma_addr_t dma; void *bufptr; - u32 pad[2]; + u32 sw_data[2]; /* Allocate descriptor */ hwdesc = knav_pool_desc_get(netcp->rx_pool); @@ -830,7 +832,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); bufptr = netdev_alloc_frag(primary_buf_len); - pad[1] = primary_buf_len; + sw_data[1] = primary_buf_len; if (unlikely(!bufptr)) { dev_warn_ratelimited(netcp->ndev_dev, @@ -842,7 +844,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (unlikely(dma_mapping_error(netcp->dev, dma))) goto fail; - pad[0] = (u32)bufptr; + sw_data[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD); @@ -852,8 +854,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) } buf_len = PAGE_SIZE; dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE); - pad[0] = (u32)page; - pad[1] = 0; + sw_data[0] = (u32)page; + sw_data[1] = 0; } desc_info = KNAV_DMA_DESC_PS_INFO_IN_DESC; @@ -863,7 +865,7 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) << KNAV_DMA_DESC_RETQ_SHIFT; set_org_pkt_info(dma, buf_len, hwdesc); - set_pad_info(pad[0], pad[1], hwdesc); + set_sw_data(sw_data[0], sw_data[1], hwdesc); set_desc_info(desc_info, pkt_info, hwdesc); /* Push to FDQs */ @@ -969,7 +971,7 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, continue; } - get_pad_info((u32 *)&skb, &tmp, desc); + get_sw_data((u32 *)&skb, &tmp, desc); netcp_free_tx_desc_chain(netcp, desc, dma_sz); if (!skb) { dev_err(netcp->ndev_dev, "No skb in Tx desc\n"); @@ -1174,7 +1176,7 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, } set_words(&tmp, 1, &desc->packet_info); - set_words((u32 *)&skb, 1, &desc->pad[0]); + set_sw_data((u32)skb, 0, desc); if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) { tmp = tx_pipe->switch_to_port; diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 343c13ac4f71..35cb9264e0d5 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -44,6 +44,7 @@ #define KNAV_DMA_NUM_EPIB_WORDS 4 #define KNAV_DMA_NUM_PS_WORDS 16 +#define KNAV_DMA_NUM_SW_DATA_WORDS 4 #define KNAV_DMA_FDQ_PER_CHAN 4 /* Tx channel scheduling priority */ @@ -142,6 +143,7 @@ struct knav_dma_cfg { * @orig_buff: buff pointer since 'buff' can be overwritten * @epib: Extended packet info block * @psdata: Protocol specific + * @sw_data: Software private data not touched by h/w */ struct knav_dma_desc { __le32 desc_info; @@ -154,7 +156,7 @@ struct knav_dma_desc { __le32 orig_buff; __le32 epib[KNAV_DMA_NUM_EPIB_WORDS]; __le32 psdata[KNAV_DMA_NUM_PS_WORDS]; - __le32 pad[4]; + u32 sw_data[KNAV_DMA_NUM_SW_DATA_WORDS]; } ____cacheline_aligned; #if IS_ENABLED(CONFIG_KEYSTONE_NAVIGATOR_DMA) From 0632448134d0ac1450a19d26f90948fde3b558ad Mon Sep 17 00:00:00 2001 From: "Karicheri, Muralidharan" Date: Fri, 19 Feb 2016 12:58:44 -0500 Subject: [PATCH 370/489] net: netcp: rework the code for get/set sw_data in dma desc SW data field in descriptor can be used by software to hold private data for the driver. As there are 4 words available for this purpose, use separate macros to place it or retrieve the same to/from descriptors. Also do type cast of data types accordingly. Cc: Wingman Kwok Cc: Mugunthan V N CC: Arnd Bergmann CC: Grygorii Strashko CC: David Laight Signed-off-by: Murali Karicheri Acked-by: Arnd Bergmann Signed-off-by: David S. Miller --- drivers/net/ethernet/ti/netcp_core.c | 72 +++++++++++++++++++++------- 1 file changed, 55 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 84bab29995fd..029841f98c32 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -117,13 +117,18 @@ static void get_pkt_info(dma_addr_t *buff, u32 *buff_len, dma_addr_t *ndesc, *ndesc = le32_to_cpu(desc->next_desc); } -static void get_sw_data(u32 *data0, u32 *data1, struct knav_dma_desc *desc) +static u32 get_sw_data(int index, struct knav_dma_desc *desc) { /* No Endian conversion needed as this data is untouched by hw */ - *data0 = desc->sw_data[0]; - *data1 = desc->sw_data[1]; + return desc->sw_data[index]; } +/* use these macros to get sw data */ +#define GET_SW_DATA0(desc) get_sw_data(0, desc) +#define GET_SW_DATA1(desc) get_sw_data(1, desc) +#define GET_SW_DATA2(desc) get_sw_data(2, desc) +#define GET_SW_DATA3(desc) get_sw_data(3, desc) + static void get_org_pkt_info(dma_addr_t *buff, u32 *buff_len, struct knav_dma_desc *desc) { @@ -154,13 +159,18 @@ static void set_desc_info(u32 desc_info, u32 pkt_info, desc->packet_info = cpu_to_le32(pkt_info); } -static void set_sw_data(u32 data0, u32 data1, struct knav_dma_desc *desc) +static void set_sw_data(int index, u32 data, struct knav_dma_desc *desc) { /* No Endian conversion needed as this data is untouched by hw */ - desc->sw_data[0] = data0; - desc->sw_data[1] = data1; + desc->sw_data[index] = data; } +/* use these macros to set sw data */ +#define SET_SW_DATA0(data, desc) set_sw_data(0, data, desc) +#define SET_SW_DATA1(data, desc) set_sw_data(1, data, desc) +#define SET_SW_DATA2(data, desc) set_sw_data(2, data, desc) +#define SET_SW_DATA3(data, desc) set_sw_data(3, data, desc) + static void set_org_pkt_info(dma_addr_t buff, u32 buff_len, struct knav_dma_desc *desc) { @@ -583,12 +593,20 @@ static void netcp_free_rx_desc_chain(struct netcp_intf *netcp, break; } get_pkt_info(&dma_buf, &tmp, &dma_desc, ndesc); - get_sw_data((u32 *)&buf_ptr, &buf_len, ndesc); + /* warning!!!! We are retrieving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + buf_ptr = (void *)GET_SW_DATA0(ndesc); + buf_len = (int)GET_SW_DATA1(desc); dma_unmap_page(netcp->dev, dma_buf, PAGE_SIZE, DMA_FROM_DEVICE); __free_page(buf_ptr); knav_pool_desc_put(netcp->rx_pool, desc); } - get_sw_data((u32 *)&buf_ptr, &buf_len, desc); + /* warning!!!! We are retrieving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + buf_ptr = (void *)GET_SW_DATA0(desc); + buf_len = (int)GET_SW_DATA1(desc); if (buf_ptr) netcp_frag_free(buf_len <= PAGE_SIZE, buf_ptr); @@ -628,7 +646,6 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) struct netcp_packet p_info; struct sk_buff *skb; void *org_buf_ptr; - u32 tmp; dma_desc = knav_queue_pop(netcp->rx_queue, &dma_sz); if (!dma_desc) @@ -641,7 +658,11 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, desc); - get_sw_data((u32 *)&org_buf_ptr, &org_buf_len, desc); + /* warning!!!! We are retrieving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + org_buf_ptr = (void *)GET_SW_DATA0(desc); + org_buf_len = (int)GET_SW_DATA1(desc); if (unlikely(!org_buf_ptr)) { dev_err(netcp->ndev_dev, "NULL bufptr in desc\n"); @@ -674,7 +695,10 @@ static int netcp_process_one_rx_packet(struct netcp_intf *netcp) } get_pkt_info(&dma_buff, &buf_len, &dma_desc, ndesc); - get_sw_data((u32 *)&page, &tmp, ndesc); + /* warning!!!! We are retrieving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + page = (struct page *)GET_SW_DATA0(desc); if (likely(dma_buff && buf_len && page)) { dma_unmap_page(netcp->dev, dma_buff, PAGE_SIZE, @@ -752,7 +776,6 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) unsigned int buf_len, dma_sz; dma_addr_t dma; void *buf_ptr; - u32 tmp; /* Allocate descriptor */ while ((dma = knav_queue_pop(netcp->rx_fdq[fdq], &dma_sz))) { @@ -763,7 +786,10 @@ static void netcp_free_rx_buf(struct netcp_intf *netcp, int fdq) } get_org_pkt_info(&dma, &buf_len, desc); - get_sw_data((u32 *)&buf_ptr, &tmp, desc); + /* warning!!!! We are retrieving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + buf_ptr = (void *)GET_SW_DATA0(desc); if (unlikely(!dma)) { dev_err(netcp->ndev_dev, "NULL orig_buff in desc\n"); @@ -844,6 +870,9 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) if (unlikely(dma_mapping_error(netcp->dev, dma))) goto fail; + /* warning!!!! We are saving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ sw_data[0] = (u32)bufptr; } else { /* Allocate a secondary receive queue entry */ @@ -854,6 +883,9 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) } buf_len = PAGE_SIZE; dma = dma_map_page(netcp->dev, page, 0, buf_len, DMA_TO_DEVICE); + /* warning!!!! We are saving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ sw_data[0] = (u32)page; sw_data[1] = 0; } @@ -865,7 +897,8 @@ static int netcp_allocate_rx_buf(struct netcp_intf *netcp, int fdq) pkt_info |= (netcp->rx_queue_id & KNAV_DMA_DESC_RETQ_MASK) << KNAV_DMA_DESC_RETQ_SHIFT; set_org_pkt_info(dma, buf_len, hwdesc); - set_sw_data(sw_data[0], sw_data[1], hwdesc); + SET_SW_DATA0(sw_data[0], hwdesc); + SET_SW_DATA1(sw_data[1], hwdesc); set_desc_info(desc_info, pkt_info, hwdesc); /* Push to FDQs */ @@ -958,7 +991,6 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, unsigned int dma_sz; dma_addr_t dma; int pkts = 0; - u32 tmp; while (budget--) { dma = knav_queue_pop(netcp->tx_compl_q, &dma_sz); @@ -971,7 +1003,10 @@ static int netcp_process_tx_compl_packets(struct netcp_intf *netcp, continue; } - get_sw_data((u32 *)&skb, &tmp, desc); + /* warning!!!! We are retrieving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + skb = (struct sk_buff *)GET_SW_DATA0(desc); netcp_free_tx_desc_chain(netcp, desc, dma_sz); if (!skb) { dev_err(netcp->ndev_dev, "No skb in Tx desc\n"); @@ -1176,7 +1211,10 @@ static int netcp_tx_submit_skb(struct netcp_intf *netcp, } set_words(&tmp, 1, &desc->packet_info); - set_sw_data((u32)skb, 0, desc); + /* warning!!!! We are saving the virtual ptr in the sw_data + * field as a 32bit value. Will not work on 64bit machines + */ + SET_SW_DATA0((u32)skb, desc); if (tx_pipe->flags & SWITCH_TO_PORT_IN_TAGINFO) { tmp = tx_pipe->switch_to_port; From 14112ca5625db8a7fbdc724783510751577a8a1b Mon Sep 17 00:00:00 2001 From: Shrikrishna Khare Date: Fri, 19 Feb 2016 11:19:52 -0800 Subject: [PATCH 371/489] Driver: Vmxnet3: Update Rx ring 2 max size Device emulation supports max size of 4096. Signed-off-by: Shrikrishna Khare Signed-off-by: Bhavesh Davda Signed-off-by: David S. Miller --- drivers/net/vmxnet3/vmxnet3_defs.h | 2 +- drivers/net/vmxnet3/vmxnet3_int.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h b/drivers/net/vmxnet3/vmxnet3_defs.h index 221a53025fd0..72ba8ae7f09a 100644 --- a/drivers/net/vmxnet3/vmxnet3_defs.h +++ b/drivers/net/vmxnet3/vmxnet3_defs.h @@ -377,7 +377,7 @@ union Vmxnet3_GenericDesc { #define VMXNET3_TX_RING_MAX_SIZE 4096 #define VMXNET3_TC_RING_MAX_SIZE 4096 #define VMXNET3_RX_RING_MAX_SIZE 4096 -#define VMXNET3_RX_RING2_MAX_SIZE 2048 +#define VMXNET3_RX_RING2_MAX_SIZE 4096 #define VMXNET3_RC_RING_MAX_SIZE 8192 /* a list of reasons for queue stop */ diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h index bdb8a6c0f8aa..729c344e6774 100644 --- a/drivers/net/vmxnet3/vmxnet3_int.h +++ b/drivers/net/vmxnet3/vmxnet3_int.h @@ -69,10 +69,10 @@ /* * Version numbers */ -#define VMXNET3_DRIVER_VERSION_STRING "1.4.5.0-k" +#define VMXNET3_DRIVER_VERSION_STRING "1.4.6.0-k" /* a 32-bit int, each byte encode a verion number in VMXNET3_DRIVER_VERSION */ -#define VMXNET3_DRIVER_VERSION_NUM 0x01040500 +#define VMXNET3_DRIVER_VERSION_NUM 0x01040600 #if defined(CONFIG_PCI_MSI) /* RSS only makes sense if MSI-X is supported. */ From 1ad5466812c0b4d7851f98573be6a332e82bc920 Mon Sep 17 00:00:00 2001 From: Ken Kawasaki Date: Sat, 20 Feb 2016 19:14:36 +0900 Subject: [PATCH 372/489] fmvj18x_cs: fix incorrect indexing of dev->dev_addr[] when copying the MAC address fix incorrect indexing of dev->dev_addr[] when copying the MAC address of FMV-J182 at buf[5]. Signed-off-by: Ken Kawasaki Signed-off-by: David S. Miller --- drivers/net/ethernet/fujitsu/fmvj18x_cs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c index a7139f588ad2..678f5018d0be 100644 --- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c +++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c @@ -469,8 +469,8 @@ static int fmvj18x_config(struct pcmcia_device *link) goto failed; } /* Read MACID from CIS */ - for (i = 5; i < 11; i++) - dev->dev_addr[i] = buf[i]; + for (i = 0; i < 6; i++) + dev->dev_addr[i] = buf[i + 5]; kfree(buf); } else { if (pcmcia_get_mac_from_cis(link, dev)) From b5a099c67a1c36b91356624ce86eb3f9f48a82c7 Mon Sep 17 00:00:00 2001 From: Robert Jarzmik Date: Sat, 20 Feb 2016 21:45:26 +0100 Subject: [PATCH 373/489] net: ethernet: davicom: fix devicetree irq resource MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The dm9000 driver doesn't work in at least one device-tree configuration, spitting an error message on irq resource : [    1.062495] dm9000 8000000.ethernet: insufficient resources [    1.068439] dm9000 8000000.ethernet: not found (-2). [    1.073451] dm9000: probe of 8000000.ethernet failed with error -2 The reason behind is that the interrupt might be provided by a gpio controller, not probed when dm9000 is probed, and needing the probe deferral mechanism to apply. Currently, the interrupt is directly taken from resources. This patch changes this to use the more generic platform_get_irq(), which handles the deferral. Moreover, since commit Fixes: 7085a7401ba5 ("drivers: platform: parse IRQ flags from resources"), the interrupt trigger flags are honored in platform_get_irq(), so remove the needless code in dm9000. Signed-off-by: Robert Jarzmik Acked-by: Marcel Ziswiler Cc: Sergei Shtylyov Tested-by: Sergei Ianovich Signed-off-by: David S. Miller --- drivers/net/ethernet/davicom/dm9000.c | 34 +++++++++++++-------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index cf94b72dbacd..48d91941408d 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -128,7 +128,6 @@ struct board_info { struct resource *data_res; struct resource *addr_req; /* resources requested */ struct resource *data_req; - struct resource *irq_res; int irq_wake; @@ -1300,22 +1299,16 @@ static int dm9000_open(struct net_device *dev) { struct board_info *db = netdev_priv(dev); - unsigned long irqflags = db->irq_res->flags & IRQF_TRIGGER_MASK; if (netif_msg_ifup(db)) dev_dbg(db->dev, "enabling %s\n", dev->name); - /* If there is no IRQ type specified, default to something that - * may work, and tell the user that this is a problem */ - - if (irqflags == IRQF_TRIGGER_NONE) - irqflags = irq_get_trigger_type(dev->irq); - - if (irqflags == IRQF_TRIGGER_NONE) + /* If there is no IRQ type specified, tell the user that this is a + * problem + */ + if (irq_get_trigger_type(dev->irq) == IRQF_TRIGGER_NONE) dev_warn(db->dev, "WARNING: no IRQ resource flags set.\n"); - irqflags |= IRQF_SHARED; - /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */ iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */ mdelay(1); /* delay needs by DM9000B */ @@ -1323,7 +1316,8 @@ dm9000_open(struct net_device *dev) /* Initialize DM9000 board */ dm9000_init_dm9000(dev); - if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev)) + if (request_irq(dev->irq, dm9000_interrupt, IRQF_SHARED, + dev->name, dev)) return -EAGAIN; /* Now that we have an interrupt handler hooked up we can unmask * our interrupts @@ -1500,15 +1494,22 @@ dm9000_probe(struct platform_device *pdev) db->addr_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); db->data_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - db->irq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0); - if (db->addr_res == NULL || db->data_res == NULL || - db->irq_res == NULL) { - dev_err(db->dev, "insufficient resources\n"); + if (!db->addr_res || !db->data_res) { + dev_err(db->dev, "insufficient resources addr=%p data=%p\n", + db->addr_res, db->data_res); ret = -ENOENT; goto out; } + ndev->irq = platform_get_irq(pdev, 0); + if (ndev->irq < 0) { + dev_err(db->dev, "interrupt resource unavailable: %d\n", + ndev->irq); + ret = ndev->irq; + goto out; + } + db->irq_wake = platform_get_irq(pdev, 1); if (db->irq_wake >= 0) { dev_dbg(db->dev, "wakeup irq %d\n", db->irq_wake); @@ -1570,7 +1571,6 @@ dm9000_probe(struct platform_device *pdev) /* fill in parameters for net-dev structure */ ndev->base_addr = (unsigned long)db->io_addr; - ndev->irq = db->irq_res->start; /* ensure at least we have a default set of IO routines */ dm9000_set_io(db, iosize); From 1e411f0138a1b05e805e2043f73f546dba651e27 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 15:07:25 +0200 Subject: [PATCH 374/489] bnx2x: Fix link-forcing for KR2 Currently, when link is using KR2 it cannot be forced to any speed other than 20g. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index d946bba43726..a529905a5f26 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -13807,8 +13807,10 @@ void bnx2x_period_func(struct link_params *params, struct link_vars *vars) if (CHIP_IS_E3(bp)) { struct bnx2x_phy *phy = ¶ms->phy[INT_PHY]; bnx2x_set_aer_mmd(params, phy); - if ((phy->supported & SUPPORTED_20000baseKR2_Full) && - (phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_20G)) + if (((phy->req_line_speed == SPEED_AUTO_NEG) && + (phy->speed_cap_mask & + PORT_HW_CFG_SPEED_CAPABILITY_D0_20G)) || + (phy->req_line_speed == SPEED_20000)) bnx2x_check_kr2_wa(params, vars, phy); bnx2x_check_over_curr(params, vars); if (vars->rx_tx_asic_rst) From 512ab9a001eb88e197859cefbb89b609a971251f Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 15:07:26 +0200 Subject: [PATCH 375/489] bnx2x: Fix 84833 RX CRC There's a problem in current 84833 phy configuration - in case 1Gb link is configured and jumbo-sized packets are being used, device will experience RX crc errors. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_link.c | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index a529905a5f26..b496e4a7b910 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -10416,6 +10416,32 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, vars->eee_status &= ~SHMEM_EEE_SUPPORTED_MASK; } + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) { + /* Additional settings for jumbo packets in 1000BASE-T mode */ + /* Allow rx extended length */ + bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_AUX_CTRL, &val); + val |= 0x4000; + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_AUX_CTRL, val); + /* TX FIFO Elasticity LSB */ + bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_1G_100T_EXT_CTRL, &val); + val |= 0x1; + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_1G_100T_EXT_CTRL, val); + /* TX FIFO Elasticity MSB */ + /* Enable expansion register 0x46 (Pattern Generator status) */ + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_EXPANSION_REG_ACCESS, 0xf46); + + bnx2x_cl45_read(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_EXPANSION_REG_RD_RW, &val); + val |= 0x4000; + bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD, + MDIO_AN_REG_8481_EXPANSION_REG_RD_RW, val); + } + if (bnx2x_is_8483x_8485x(phy)) { /* Bring PHY out of super isolate mode as the final step. */ bnx2x_cl45_read_and_write(bp, phy, From 27ba2d2df0d7882008d9cf21f7dc05711415eeac Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 15:07:27 +0200 Subject: [PATCH 376/489] bnx2x: Correct 84858 PHY fw version The phy's firmware version isn't being parsed properly as it's currently parsed like the rest of the 848xx phys. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_link.c | 92 ++++++++++++++++--- 1 file changed, 79 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index b496e4a7b910..0c7b1c706142 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -6185,26 +6185,80 @@ static int bnx2x_format_ver(u32 num, u8 *str, u16 *len) shift -= 4; digit = ((num & mask) >> shift); if (digit == 0 && remove_leading_zeros) { - mask = mask >> 4; - continue; - } else if (digit < 0xa) - *str_ptr = digit + '0'; - else - *str_ptr = digit - 0xa + 'a'; - remove_leading_zeros = 0; - str_ptr++; - (*len)--; + *str_ptr = '0'; + } else { + if (digit < 0xa) + *str_ptr = digit + '0'; + else + *str_ptr = digit - 0xa + 'a'; + + remove_leading_zeros = 0; + str_ptr++; + (*len)--; + } mask = mask >> 4; if (shift == 4*4) { + if (remove_leading_zeros) { + str_ptr++; + (*len)--; + } *str_ptr = '.'; str_ptr++; (*len)--; remove_leading_zeros = 1; } } + if (remove_leading_zeros) + (*len)--; return 0; } +static int bnx2x_3_seq_format_ver(u32 num, u8 *str, u16 *len) +{ + u8 *str_ptr = str; + u32 mask = 0x00f00000; + u8 shift = 8*3; + u8 digit; + u8 remove_leading_zeros = 1; + + if (*len < 10) { + /* Need more than 10chars for this format */ + *str_ptr = '\0'; + (*len)--; + return -EINVAL; + } + + while (shift > 0) { + shift -= 4; + digit = ((num & mask) >> shift); + if (digit == 0 && remove_leading_zeros) { + *str_ptr = '0'; + } else { + if (digit < 0xa) + *str_ptr = digit + '0'; + else + *str_ptr = digit - 0xa + 'a'; + + remove_leading_zeros = 0; + str_ptr++; + (*len)--; + } + mask = mask >> 4; + if ((shift == 4*4) || (shift == 4*2)) { + if (remove_leading_zeros) { + str_ptr++; + (*len)--; + } + *str_ptr = '.'; + str_ptr++; + (*len)--; + remove_leading_zeros = 1; + } + } + if (remove_leading_zeros) + (*len)--; + return 0; +} static int bnx2x_null_format_ver(u32 spirom_ver, u8 *str, u16 *len) { @@ -9677,8 +9731,9 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, if (bnx2x_is_8483x_8485x(phy)) { bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, 0x400f, &fw_ver1); - bnx2x_save_spirom_version(bp, port, fw_ver1 & 0xfff, - phy->ver_addr); + if (phy->type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) + fw_ver1 &= 0xfff; + bnx2x_save_spirom_version(bp, port, fw_ver1, phy->ver_addr); } else { /* For 32-bit registers in 848xx, access via MDIO2ARM i/f. */ /* (1) set reg 0xc200_0014(SPI_BRIDGE_CTRL_2) to 0x03000000 */ @@ -9775,7 +9830,7 @@ static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; switch (action) { case PHY_INIT: - if (!bnx2x_is_8483x_8485x(phy)) { + if (bnx2x_is_8483x_8485x(phy)) { /* Save spirom version */ bnx2x_save_848xx_spirom_version(phy, bp, params->port); } @@ -10581,6 +10636,17 @@ static u8 bnx2x_848xx_read_status(struct bnx2x_phy *phy, return link_up; } +static int bnx2x_8485x_format_ver(u32 raw_ver, u8 *str, u16 *len) +{ + int status = 0; + u32 num; + + num = ((raw_ver & 0xF80) >> 7) << 16 | ((raw_ver & 0x7F) << 8) | + ((raw_ver & 0xF000) >> 12); + status = bnx2x_3_seq_format_ver(num, str, len); + return status; +} + static int bnx2x_848xx_format_ver(u32 raw_ver, u8 *str, u16 *len) { int status = 0; @@ -12008,7 +12074,7 @@ static const struct bnx2x_phy phy_84858 = { .read_status = (read_status_t)bnx2x_848xx_read_status, .link_reset = (link_reset_t)bnx2x_848x3_link_reset, .config_loopback = (config_loopback_t)NULL, - .format_fw_ver = (format_fw_ver_t)bnx2x_848xx_format_ver, + .format_fw_ver = (format_fw_ver_t)bnx2x_8485x_format_ver, .hw_reset = (hw_reset_t)bnx2x_84833_hw_reset_phy, .set_link_led = (set_link_led_t)bnx2x_848xx_set_link_led, .phy_specific_func = (phy_specific_func_t)bnx2x_848xx_specific_func From bb1187af658f9ed05a24ab0f25d3b41324176590 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 15:07:28 +0200 Subject: [PATCH 377/489] bnx2x: Fix led setting for 84858 phy. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_link.c | 94 ++++++++++++++++++- .../net/ethernet/broadcom/bnx2x/bnx2x_reg.h | 2 + 2 files changed, 91 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 0c7b1c706142..8779f154fcae 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -9787,16 +9787,32 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy, static void bnx2x_848xx_set_led(struct bnx2x *bp, struct bnx2x_phy *phy) { - u16 val, offset, i; + u16 val, led3_blink_rate, offset, i; static struct bnx2x_reg_set reg_set[] = { {MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED1_MASK, 0x0080}, {MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED2_MASK, 0x0018}, {MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED3_MASK, 0x0006}, - {MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED3_BLINK, 0x0000}, {MDIO_PMA_DEVAD, MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH, MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ}, {MDIO_AN_DEVAD, 0xFFFB, 0xFFFD} }; + + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) { + /* Set LED5 source */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED5_MASK, + 0x90); + led3_blink_rate = 0x000f; + } else { + led3_blink_rate = 0x0000; + } + /* Set LED3 BLINK */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_BLINK, + led3_blink_rate); + /* PHYC_CTL_LED_CTL */ bnx2x_cl45_read(bp, phy, MDIO_PMA_DEVAD, @@ -9804,6 +9820,9 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp, val &= 0xFE00; val |= 0x0092; + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) + val |= 2 << 12; /* LED5 ON based on source */ + bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LINK_SIGNAL, val); @@ -9817,10 +9836,17 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp, else offset = MDIO_PMA_REG_84823_CTL_LED_CTL_1; - /* stretch_en for LED3*/ + if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) + val = MDIO_PMA_REG_84858_ALLOW_GPHY_ACT | + MDIO_PMA_REG_84823_LED3_STRETCH_EN; + else + val = MDIO_PMA_REG_84823_LED3_STRETCH_EN; + + /* stretch_en for LEDs */ bnx2x_cl45_read_or_write(bp, phy, - MDIO_PMA_DEVAD, offset, - MDIO_PMA_REG_84823_LED3_STRETCH_EN); + MDIO_PMA_DEVAD, + offset, + val); } static void bnx2x_848xx_specific_func(struct bnx2x_phy *phy, @@ -10743,10 +10769,25 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, 0x0); } else { + /* LED 1 OFF */ bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LED1_MASK, 0x0); + + if (phy->type == + PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) { + /* LED 2 OFF */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED2_MASK, + 0x0); + /* LED 3 OFF */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x0); + } } break; case LED_MODE_FRONT_PANEL_OFF: @@ -10805,6 +10846,19 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, MDIO_PMA_REG_8481_SIGNAL_MASK, 0x0); } + if (phy->type == + PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) { + /* LED 2 OFF */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED2_MASK, + 0x0); + /* LED 3 OFF */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x0); + } } break; case LED_MODE_ON: @@ -10868,6 +10922,25 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, params->port*4, NIG_MASK_MI_INT); } + } + if (phy->type == + PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) { + /* Tell LED3 to constant on */ + bnx2x_cl45_read(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LINK_SIGNAL, + &val); + val &= ~(7<<6); + val |= (2<<6); /* A83B[8:6]= 2 */ + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LINK_SIGNAL, + val); + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x20); + } else { bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_SIGNAL_MASK, @@ -10945,6 +11018,17 @@ static void bnx2x_848xx_set_link_led(struct bnx2x_phy *phy, MDIO_PMA_DEVAD, MDIO_PMA_REG_8481_LINK_SIGNAL, val); + if (phy->type == + PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84858) { + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED2_MASK, + 0x18); + bnx2x_cl45_write(bp, phy, + MDIO_PMA_DEVAD, + MDIO_PMA_REG_8481_LED3_MASK, + 0x06); + } if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84834) { /* Restore LED4 source to external link, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index 4dead49bd5cb..d27d40e4a78e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -7296,6 +7296,8 @@ Theotherbitsarereservedandshouldbezero*/ #define MDIO_PMA_REG_84823_CTL_LED_CTL_1 0xa8e3 #define MDIO_PMA_REG_84833_CTL_LED_CTL_1 0xa8ec #define MDIO_PMA_REG_84823_LED3_STRETCH_EN 0x0080 +/* BCM84858 only */ +#define MDIO_PMA_REG_84858_ALLOW_GPHY_ACT 0x8000 /* BCM84833 only */ #define MDIO_84833_TOP_CFG_FW_REV 0x400f From 4ec0b6d506186de559b331bd08f8483463116f72 Mon Sep 17 00:00:00 2001 From: Yuval Mintz Date: Sun, 21 Feb 2016 15:07:29 +0200 Subject: [PATCH 378/489] bnx2x: Fix 84833 phy command handler Current initialization sequence is lacking, causing some configurations to fail. Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- .../net/ethernet/broadcom/bnx2x/bnx2x_link.c | 81 ++++++++++++------- .../net/ethernet/broadcom/bnx2x/bnx2x_reg.h | 4 + 2 files changed, 56 insertions(+), 29 deletions(-) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c index 8779f154fcae..1fb80100e5e7 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c @@ -10117,15 +10117,20 @@ static int bnx2x_84858_cmd_hdlr(struct bnx2x_phy *phy, static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy, struct link_params *params, u16 fw_cmd, - u16 cmd_args[], int argc) + u16 cmd_args[], int argc, int process) { int idx; u16 val; struct bnx2x *bp = params->bp; - /* Write CMD_OPEN_OVERRIDE to STATUS reg */ - bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_848xx_CMD_HDLR_STATUS, - PHY84833_STATUS_CMD_OPEN_OVERRIDE); + int rc = 0; + + if (process == PHY84833_MB_PROCESS2) { + /* Write CMD_OPEN_OVERRIDE to STATUS reg */ + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_STATUS, + PHY84833_STATUS_CMD_OPEN_OVERRIDE); + } + for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) { bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, MDIO_848xx_CMD_HDLR_STATUS, &val); @@ -10135,15 +10140,27 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy, } if (idx >= PHY848xx_CMDHDLR_WAIT) { DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n"); + /* if the status is CMD_COMPLETE_PASS or CMD_COMPLETE_ERROR + * clear the status to CMD_CLEAR_COMPLETE + */ + if (val == PHY84833_STATUS_CMD_COMPLETE_PASS || + val == PHY84833_STATUS_CMD_COMPLETE_ERROR) { + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_STATUS, + PHY84833_STATUS_CMD_CLEAR_COMPLETE); + } return -EINVAL; } - - /* Prepare argument(s) and issue command */ - for (idx = 0; idx < argc; idx++) { - bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_848xx_CMD_HDLR_DATA1 + idx, - cmd_args[idx]); + if (process == PHY84833_MB_PROCESS1 || + process == PHY84833_MB_PROCESS2) { + /* Prepare argument(s) */ + for (idx = 0; idx < argc; idx++) { + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_DATA1 + idx, + cmd_args[idx]); + } } + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, MDIO_848xx_CMD_HDLR_COMMAND, fw_cmd); for (idx = 0; idx < PHY848xx_CMDHDLR_WAIT; idx++) { @@ -10157,24 +10174,30 @@ static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy, if ((idx >= PHY848xx_CMDHDLR_WAIT) || (val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) { DP(NETIF_MSG_LINK, "FW cmd failed.\n"); - return -EINVAL; + rc = -EINVAL; } - /* Gather returning data */ - for (idx = 0; idx < argc; idx++) { - bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, - MDIO_848xx_CMD_HDLR_DATA1 + idx, - &cmd_args[idx]); + if (process == PHY84833_MB_PROCESS3 && rc == 0) { + /* Gather returning data */ + for (idx = 0; idx < argc; idx++) { + bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_DATA1 + idx, + &cmd_args[idx]); + } } - bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, - MDIO_848xx_CMD_HDLR_STATUS, - PHY84833_STATUS_CMD_CLEAR_COMPLETE); - return 0; + if (val == PHY84833_STATUS_CMD_COMPLETE_ERROR || + val == PHY84833_STATUS_CMD_COMPLETE_PASS) { + bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD, + MDIO_848xx_CMD_HDLR_STATUS, + PHY84833_STATUS_CMD_CLEAR_COMPLETE); + } + return rc; } static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy, struct link_params *params, u16 fw_cmd, - u16 cmd_args[], int argc) + u16 cmd_args[], int argc, + int process) { struct bnx2x *bp = params->bp; @@ -10187,7 +10210,7 @@ static int bnx2x_848xx_cmd_hdlr(struct bnx2x_phy *phy, argc); } else { return bnx2x_84833_cmd_hdlr(phy, params, fw_cmd, cmd_args, - argc); + argc, process); } } @@ -10214,7 +10237,7 @@ static int bnx2x_848xx_pair_swap_cfg(struct bnx2x_phy *phy, status = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_PAIR_SWAP, data, - PHY848xx_CMDHDLR_MAX_ARGS); + 2, PHY84833_MB_PROCESS2); if (status == 0) DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data[1]); @@ -10303,8 +10326,8 @@ static int bnx2x_8483x_disable_eee(struct bnx2x_phy *phy, DP(NETIF_MSG_LINK, "Don't Advertise 10GBase-T EEE\n"); /* Prevent Phy from working in EEE and advertising it */ - rc = bnx2x_848xx_cmd_hdlr(phy, params, - PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1); + rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE, + &cmd_args, 1, PHY84833_MB_PROCESS1); if (rc) { DP(NETIF_MSG_LINK, "EEE disable failed.\n"); return rc; @@ -10321,8 +10344,8 @@ static int bnx2x_8483x_enable_eee(struct bnx2x_phy *phy, struct bnx2x *bp = params->bp; u16 cmd_args = 1; - rc = bnx2x_848xx_cmd_hdlr(phy, params, - PHY848xx_CMD_SET_EEE_MODE, &cmd_args, 1); + rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE, + &cmd_args, 1, PHY84833_MB_PROCESS1); if (rc) { DP(NETIF_MSG_LINK, "EEE enable failed.\n"); return rc; @@ -10443,7 +10466,7 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy, cmd_args[3] = PHY84833_CONSTANT_LATENCY; rc = bnx2x_848xx_cmd_hdlr(phy, params, PHY848xx_CMD_SET_EEE_MODE, cmd_args, - PHY848xx_CMDHDLR_MAX_ARGS); + 4, PHY84833_MB_PROCESS1); if (rc) DP(NETIF_MSG_LINK, "Cfg AutogrEEEn failed.\n"); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h index d27d40e4a78e..a43dea259b12 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h @@ -7339,6 +7339,10 @@ Theotherbitsarereservedandshouldbezero*/ #define PHY84833_STATUS_CMD_NOT_OPEN_FOR_CMDS 0x0040 #define PHY84833_STATUS_CMD_CLEAR_COMPLETE 0x0080 #define PHY84833_STATUS_CMD_OPEN_OVERRIDE 0xa5a5 +/* Mailbox Process */ +#define PHY84833_MB_PROCESS1 1 +#define PHY84833_MB_PROCESS2 2 +#define PHY84833_MB_PROCESS3 3 /* Mailbox status set used by 84858 only */ #define PHY84858_STATUS_CMD_RECEIVED 0x0001 From f6bf0fa14cf848ae770e0b7842c9b11ce2f01645 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Fri, 12 Feb 2016 16:03:05 +1100 Subject: [PATCH 379/489] powerpc/eeh: Fix partial hotplug criterion During error recovery, the device could be removed as part of the partial hotplug. The criterion used to come with partial hotplug is: if the device driver provides error_detected(), slot_reset() and resume() callbacks, it's immune from hotplug. Otherwise, it's going to experience partial hotplug during EEH recovery. But the criterion isn't correct enough: mlx4_core driver for Mellanox adapters provides error_detected(), slot_reset() callbacks, but resume() isn't there. Those Mellanox adapters won't be to involved in the partial hotplug. This fixes the criterion to a practical one: adpater with driver that provides error_detected(), slot_reset() will be immune from partial hotplug. resume() isn't mandatory. Fixes: f2da4ccf ("powerpc/eeh: More relaxed hotplug criterion") Cc: stable@vger.kernel.org #v4.4+ Signed-off-by: Gavin Shan Signed-off-by: Michael Ellerman --- arch/powerpc/kernel/eeh_driver.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c index f69ecaa7ce33..52c1e273f8cd 100644 --- a/arch/powerpc/kernel/eeh_driver.c +++ b/arch/powerpc/kernel/eeh_driver.c @@ -418,8 +418,7 @@ static void *eeh_rmv_device(void *data, void *userdata) eeh_pcid_put(dev); if (driver->err_handler && driver->err_handler->error_detected && - driver->err_handler->slot_reset && - driver->err_handler->resume) + driver->err_handler->slot_reset) return NULL; } From 9ab3ac233a8b4ffcc27c8475b83dee49fc46bc76 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Sat, 20 Feb 2016 20:41:54 +0530 Subject: [PATCH 380/489] powerpc/mm/hash: Clear the invalid slot information correctly We can get a hash pte fault with 4k base page size and find the pte already inserted with 64K base page size. In that case we need to clear the existing slot information from the old pte. Fix this correctly With THP, we also clear the slot information with respect to all the 64K hash pte mapping that 16MB page. They are all invalid now. This make sure we don't find the slot valid when we fault with 4k base page size. Finding the slot valid should not result in any wrong behavior because we do check again in hash page table for the validity. But we can avoid that check completely. Fixes: a43c0eb8364c022 ("powerpc/mm: Convert 4k hash insert to C") Signed-off-by: Aneesh Kumar K.V Signed-off-by: Michael Ellerman --- arch/powerpc/mm/hash64_64k.c | 8 +++++++- arch/powerpc/mm/hugepage-hash64.c | 12 +++++++++++- 2 files changed, 18 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c index 0762c1e08c88..edb09912f0c9 100644 --- a/arch/powerpc/mm/hash64_64k.c +++ b/arch/powerpc/mm/hash64_64k.c @@ -111,7 +111,13 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid, */ if (!(old_pte & _PAGE_COMBO)) { flush_hash_page(vpn, rpte, MMU_PAGE_64K, ssize, flags); - old_pte &= ~_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND; + /* + * clear the old slot details from the old and new pte. + * On hash insert failure we use old pte value and we don't + * want slot information there if we have a insert failure. + */ + old_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND); + new_pte &= ~(_PAGE_HASHPTE | _PAGE_F_GIX | _PAGE_F_SECOND); goto htab_insert_hpte; } /* diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c index 49b152b0f926..eb2accdd76fd 100644 --- a/arch/powerpc/mm/hugepage-hash64.c +++ b/arch/powerpc/mm/hugepage-hash64.c @@ -78,9 +78,19 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid, * base page size. This is because demote_segment won't flush * hash page table entries. */ - if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) + if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO)) { flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K, ssize, flags); + /* + * With THP, we also clear the slot information with + * respect to all the 64K hash pte mapping the 16MB + * page. They are all invalid now. This make sure we + * don't find the slot valid when we fault with 4k + * base page size. + * + */ + memset(hpte_slot_array, 0, PTE_FRAG_SIZE); + } } valid = hpte_valid(hpte_slot_array, index); From 342300cc9cd3428bc6bfe5809bfcc1b9a0f06702 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 19 Feb 2016 14:44:14 +0100 Subject: [PATCH 381/489] s390/compat: correct restore of high gprs on signal return git commit 8070361799ae1e3f4ef347bd10f0a508ac10acfb "s390: add support for vector extension" broke 31-bit compat processes in regard to signal handling. The restore_sigregs_ext32() function is used to restore the additional elements from the user space signal frame. Among the additional elements are the upper registers halves for 64-bit register support for 31-bit processes. The copy_from_user that is used to retrieve the high-gprs array from the user stack uses an incorrect length, 8 bytes instead of 64 bytes. This causes incorrect upper register halves to get loaded. Cc: stable@vger.kernel.org # 3.8+ Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/compat_signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c index 66c94417c0ba..4af60374eba0 100644 --- a/arch/s390/kernel/compat_signal.c +++ b/arch/s390/kernel/compat_signal.c @@ -271,7 +271,7 @@ static int restore_sigregs_ext32(struct pt_regs *regs, /* Restore high gprs from signal stack */ if (__copy_from_user(&gprs_high, &sregs_ext->gprs_high, - sizeof(&sregs_ext->gprs_high))) + sizeof(sregs_ext->gprs_high))) return -EFAULT; for (i = 0; i < NUM_GPRS; i++) *(__u32 *)®s->gprs[i] = gprs_high[i]; From 1b17cb796f5d40ffa239c6926385abd83a77a49b Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Fri, 19 Feb 2016 15:29:05 +0100 Subject: [PATCH 382/489] s390/fpu: signals vs. floating point control register git commit 904818e2f229f3d94ec95f6932a6358c81e73d78 "s390/kernel: introduce fpu-internal.h with fpu helper functions" introduced the fpregs_store / fp_regs_load helper. These function fail to save and restore the floating pointer control registers. The effect is that the FPC is not correctly handled on signal delivery and signal return. Cc: stable@vger.kernel.org # 4.4 Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/fpu/internal.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/s390/include/asm/fpu/internal.h b/arch/s390/include/asm/fpu/internal.h index ea91ddfe54eb..629c90865a07 100644 --- a/arch/s390/include/asm/fpu/internal.h +++ b/arch/s390/include/asm/fpu/internal.h @@ -40,6 +40,7 @@ static inline void convert_fp_to_vx(__vector128 *vxrs, freg_t *fprs) static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) { fpregs->pad = 0; + fpregs->fpc = fpu->fpc; if (MACHINE_HAS_VX) convert_vx_to_fp((freg_t *)&fpregs->fprs, fpu->vxrs); else @@ -49,6 +50,7 @@ static inline void fpregs_store(_s390_fp_regs *fpregs, struct fpu *fpu) static inline void fpregs_load(_s390_fp_regs *fpregs, struct fpu *fpu) { + fpu->fpc = fpregs->fpc; if (MACHINE_HAS_VX) convert_fp_to_vx(fpu->vxrs, (freg_t *)&fpregs->fprs); else From 5af9a454769bb5528ba1e5268e5649414ae832bd Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Wed, 17 Feb 2016 14:17:42 +0200 Subject: [PATCH 383/489] drm/i915: Add helper to get a display power ref if it was already enabled MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit We have many places in the code where we check if a given display power domain is enabled and if so access registers backed by this power domain. We assumed that some modeset lock will prevent the power reference from vanishing in the middle of the HW access, but this assumption doesn't always hold. In such cases we get either the wakeref not held, or an unclaimed register access error message. To fix this in a future-proof way that's independent of other locks wrap any such access with a get_ref_if_enabled()/put_ref() pair. Kudos to Ville and Joonas for the ideas of this new interface. v2: - init the power_domains ptr when declaring it everywhere (Joonas) v3: - don't report the device to be powered if runtime PM is disabled CC: Mika Kuoppala CC: Chris Wilson CC: Joonas Lahtinen CC: Ville Syrjälä Signed-off-by: Imre Deak Reviewed-by: Joonas Lahtinen Link: http://patchwork.freedesktop.org/patch/msgid/1455711462-7442-1-git-send-email-imre.deak@intel.com (cherry picked from commit 09731280028ce03e6a27e1998137f1775a2839f3) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_drv.h | 3 + drivers/gpu/drm/i915/intel_runtime_pm.c | 100 +++++++++++++++++++++--- 2 files changed, 94 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h index ea5415851c6e..df7f3cb66056 100644 --- a/drivers/gpu/drm/i915/intel_drv.h +++ b/drivers/gpu/drm/i915/intel_drv.h @@ -1428,6 +1428,8 @@ bool __intel_display_power_is_enabled(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); +bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain); void intel_display_power_put(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain); @@ -1514,6 +1516,7 @@ enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv) enable_rpm_wakeref_asserts(dev_priv) void intel_runtime_pm_get(struct drm_i915_private *dev_priv); +bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv); void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv); void intel_runtime_pm_put(struct drm_i915_private *dev_priv); diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index ddbdbffe829a..89dcc99ac3ca 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -1442,6 +1442,22 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv, chv_set_pipe_power_well(dev_priv, power_well, false); } +static void +__intel_display_power_get_domain(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + struct i915_power_well *power_well; + int i; + + for_each_power_well(i, power_well, BIT(domain), power_domains) { + if (!power_well->count++) + intel_power_well_enable(dev_priv, power_well); + } + + power_domains->domain_use_count[domain]++; +} + /** * intel_display_power_get - grab a power domain reference * @dev_priv: i915 device instance @@ -1457,24 +1473,53 @@ static void chv_pipe_power_well_disable(struct drm_i915_private *dev_priv, void intel_display_power_get(struct drm_i915_private *dev_priv, enum intel_display_power_domain domain) { - struct i915_power_domains *power_domains; - struct i915_power_well *power_well; - int i; + struct i915_power_domains *power_domains = &dev_priv->power_domains; intel_runtime_pm_get(dev_priv); - power_domains = &dev_priv->power_domains; + mutex_lock(&power_domains->lock); + + __intel_display_power_get_domain(dev_priv, domain); + + mutex_unlock(&power_domains->lock); +} + +/** + * intel_display_power_get_if_enabled - grab a reference for an enabled display power domain + * @dev_priv: i915 device instance + * @domain: power domain to reference + * + * This function grabs a power domain reference for @domain and ensures that the + * power domain and all its parents are powered up. Therefore users should only + * grab a reference to the innermost power domain they need. + * + * Any power domain reference obtained by this function must have a symmetric + * call to intel_display_power_put() to release the reference again. + */ +bool intel_display_power_get_if_enabled(struct drm_i915_private *dev_priv, + enum intel_display_power_domain domain) +{ + struct i915_power_domains *power_domains = &dev_priv->power_domains; + bool is_enabled; + + if (!intel_runtime_pm_get_if_in_use(dev_priv)) + return false; mutex_lock(&power_domains->lock); - for_each_power_well(i, power_well, BIT(domain), power_domains) { - if (!power_well->count++) - intel_power_well_enable(dev_priv, power_well); + if (__intel_display_power_is_enabled(dev_priv, domain)) { + __intel_display_power_get_domain(dev_priv, domain); + is_enabled = true; + } else { + is_enabled = false; } - power_domains->domain_use_count[domain]++; - mutex_unlock(&power_domains->lock); + + if (!is_enabled) + intel_runtime_pm_put(dev_priv); + + return is_enabled; } /** @@ -2245,6 +2290,43 @@ void intel_runtime_pm_get(struct drm_i915_private *dev_priv) assert_rpm_wakelock_held(dev_priv); } +/** + * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use + * @dev_priv: i915 device instance + * + * This function grabs a device-level runtime pm reference if the device is + * already in use and ensures that it is powered up. + * + * Any runtime pm reference obtained by this function must have a symmetric + * call to intel_runtime_pm_put() to release the reference again. + */ +bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv) +{ + struct drm_device *dev = dev_priv->dev; + struct device *device = &dev->pdev->dev; + int ret; + + if (!IS_ENABLED(CONFIG_PM)) + return true; + + ret = pm_runtime_get_if_in_use(device); + + /* + * In cases runtime PM is disabled by the RPM core and we get an + * -EINVAL return value we are not supposed to call this function, + * since the power state is undefined. This applies atm to the + * late/early system suspend/resume handlers. + */ + WARN_ON_ONCE(ret < 0); + if (ret <= 0) + return false; + + atomic_inc(&dev_priv->pm.wakeref_count); + assert_rpm_wakelock_held(dev_priv); + + return true; +} + /** * intel_runtime_pm_get_noresume - grab a runtime pm reference * @dev_priv: i915 device instance From 9fb84d5a9299ac678dedc56487f394e5f68b91cb Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:11 +0200 Subject: [PATCH 384/489] drm/i915: Ensure the HW is powered during display pipe HW readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Revieved-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-3-git-send-email-imre.deak@intel.com (cherry picked from commit 1729050eb4bbc192e54069e82069f2811313c1dd) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 67 ++++++++++++++++++++-------- 1 file changed, 48 insertions(+), 19 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 5feb65725c04..892c53e3418a 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -8171,18 +8171,22 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; + ret = false; + tmp = I915_READ(PIPECONF(crtc->pipe)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; if (IS_G4X(dev) || IS_VALLEYVIEW(dev) || IS_CHERRYVIEW(dev)) { switch (tmp & PIPECONF_BPC_MASK) { @@ -8262,7 +8266,12 @@ static bool i9xx_get_pipe_config(struct intel_crtc *crtc, pipe_config->base.adjusted_mode.crtc_clock = pipe_config->port_clock / pipe_config->pixel_multiplier; - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void ironlake_init_pch_refclk(struct drm_device *dev) @@ -9366,18 +9375,21 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; + enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; + ret = false; tmp = I915_READ(PIPECONF(crtc->pipe)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; switch (tmp & PIPECONF_BPC_MASK) { case PIPECONF_6BPC: @@ -9440,7 +9452,12 @@ static bool ironlake_get_pipe_config(struct intel_crtc *crtc, ironlake_get_pfit_config(crtc, pipe_config); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) @@ -9950,12 +9967,17 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, { struct drm_device *dev = crtc->base.dev; struct drm_i915_private *dev_priv = dev->dev_private; - enum intel_display_power_domain pfit_domain; + enum intel_display_power_domain power_domain; + unsigned long power_domain_mask; uint32_t tmp; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(crtc->pipe))) + power_domain = POWER_DOMAIN_PIPE(crtc->pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + power_domain_mask = BIT(power_domain); + + ret = false; pipe_config->cpu_transcoder = (enum transcoder) crtc->pipe; pipe_config->shared_dpll = DPLL_ID_PRIVATE; @@ -9982,13 +10004,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, pipe_config->cpu_transcoder = TRANSCODER_EDP; } - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder))) - return false; + power_domain = POWER_DOMAIN_TRANSCODER(pipe_config->cpu_transcoder); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) + goto out; + power_domain_mask |= BIT(power_domain); tmp = I915_READ(PIPECONF(pipe_config->cpu_transcoder)); if (!(tmp & PIPECONF_ENABLE)) - return false; + goto out; haswell_get_ddi_port_state(crtc, pipe_config); @@ -9998,14 +10021,14 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, skl_init_scalers(dev, crtc, pipe_config); } - pfit_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe); - if (INTEL_INFO(dev)->gen >= 9) { pipe_config->scaler_state.scaler_id = -1; pipe_config->scaler_state.scaler_users &= ~(1 << SKL_CRTC_INDEX); } - if (intel_display_power_is_enabled(dev_priv, pfit_domain)) { + power_domain = POWER_DOMAIN_PIPE_PANEL_FITTER(crtc->pipe); + if (intel_display_power_get_if_enabled(dev_priv, power_domain)) { + power_domain_mask |= BIT(power_domain); if (INTEL_INFO(dev)->gen >= 9) skylake_get_pfit_config(crtc, pipe_config); else @@ -10023,7 +10046,13 @@ static bool haswell_get_pipe_config(struct intel_crtc *crtc, pipe_config->pixel_multiplier = 1; } - return true; + ret = true; + +out: + for_each_power_domain(power_domain, power_domain_mask) + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void i845_update_cursor(struct drm_crtc *crtc, u32 base, bool on) From 013ef6cfc411bfe4a6009eaa7dabb6531bbb41bb Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:12 +0200 Subject: [PATCH 385/489] drm/i915/ibx: Ensure the HW is powered during PLL HW readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-4-git-send-email-imre.deak@intel.com (cherry picked from commit 12fda3876d08519bdf6f0acc70dd35754b422ed5) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 892c53e3418a..46a84bb9ca1f 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -13659,7 +13659,7 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(PCH_DPLL(pll->id)); @@ -13667,6 +13667,8 @@ static bool ibx_pch_dpll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->fp0 = I915_READ(PCH_FP0(pll->id)); hw_state->fp1 = I915_READ(PCH_FP1(pll->id)); + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & DPLL_VCO_ENABLE; } From bacd67d6a36c8905258d08ed6ef41346fa01607c Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:13 +0200 Subject: [PATCH 386/489] drm/i915: Ensure the HW is powered when disabling VGA The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-5-git-send-email-imre.deak@intel.com (cherry picked from commit 6392f8478e6f119467b1ad06e30e1f078e62efc1) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 46a84bb9ca1f..7934c45366ff 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -15599,10 +15599,12 @@ void i915_redisable_vga(struct drm_device *dev) * level, just check if the power well is enabled instead of trying to * follow the "don't touch the power well if we don't need it" policy * the rest of the driver uses. */ - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_VGA)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_VGA)) return; i915_redisable_vga_power_on(dev); + + intel_display_power_put(dev_priv, POWER_DOMAIN_VGA); } static bool primary_get_hw_state(struct intel_plane *plane) From 5a24fab098d6f1aeae3e184a704cf2cd1f677ecd Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:14 +0200 Subject: [PATCH 387/489] drm/i915: Ensure the HW is powered during HW access in assert_pipe The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-6-git-send-email-imre.deak@intel.com (cherry picked from commit 4feed0ebfa45879bc422c9a0bfa3cffec82ea60a) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_display.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 7934c45366ff..46947fffd599 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -1351,18 +1351,21 @@ void assert_pipe(struct drm_i915_private *dev_priv, bool cur_state; enum transcoder cpu_transcoder = intel_pipe_to_cpu_transcoder(dev_priv, pipe); + enum intel_display_power_domain power_domain; /* if we need the pipe quirk it must be always on */ if ((pipe == PIPE_A && dev_priv->quirks & QUIRK_PIPEA_FORCE) || (pipe == PIPE_B && dev_priv->quirks & QUIRK_PIPEB_FORCE)) state = true; - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_TRANSCODER(cpu_transcoder))) { - cur_state = false; - } else { + power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder); + if (intel_display_power_get_if_enabled(dev_priv, power_domain)) { u32 val = I915_READ(PIPECONF(cpu_transcoder)); cur_state = !!(val & PIPECONF_ENABLE); + + intel_display_power_put(dev_priv, power_domain); + } else { + cur_state = false; } I915_STATE_WARN(cur_state != state, From 7a6252c6bce1124eebf620948280f8255a83f04a Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:15 +0200 Subject: [PATCH 388/489] drm/i915/crt: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93439 CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-7-git-send-email-imre.deak@intel.com (cherry picked from commit 1c8fdda1ea947ae8cf994969a1c285acc7089cb9) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_crt.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c index 9c89df1af036..a7b4a524fadd 100644 --- a/drivers/gpu/drm/i915/intel_crt.c +++ b/drivers/gpu/drm/i915/intel_crt.c @@ -71,22 +71,29 @@ static bool intel_crt_get_hw_state(struct intel_encoder *encoder, struct intel_crt *crt = intel_encoder_to_crt(encoder); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(crt->adpa_reg); if (!(tmp & ADPA_DAC_ENABLE)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static unsigned int intel_crt_get_flags(struct intel_encoder *encoder) From d59410219ae396a5649eecff1a041e4588aff999 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:16 +0200 Subject: [PATCH 389/489] drm/i915/ddi: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-8-git-send-email-imre.deak@intel.com (cherry picked from commit e27daab49718e3232318d8b539cb302521b4b724) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_ddi.c | 112 ++++++++++++++++++++++--------- 1 file changed, 79 insertions(+), 33 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c index 54a165b9c92d..0f3df2c39f7c 100644 --- a/drivers/gpu/drm/i915/intel_ddi.c +++ b/drivers/gpu/drm/i915/intel_ddi.c @@ -1969,13 +1969,16 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) enum transcoder cpu_transcoder; enum intel_display_power_domain power_domain; uint32_t tmp; + bool ret; power_domain = intel_display_port_power_domain(intel_encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; - if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) - return false; + if (!intel_encoder->get_hw_state(intel_encoder, &pipe)) { + ret = false; + goto out; + } if (port == PORT_A) cpu_transcoder = TRANSCODER_EDP; @@ -1987,23 +1990,33 @@ bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector) switch (tmp & TRANS_DDI_MODE_SELECT_MASK) { case TRANS_DDI_MODE_SELECT_HDMI: case TRANS_DDI_MODE_SELECT_DVI: - return (type == DRM_MODE_CONNECTOR_HDMIA); + ret = type == DRM_MODE_CONNECTOR_HDMIA; + break; case TRANS_DDI_MODE_SELECT_DP_SST: - if (type == DRM_MODE_CONNECTOR_eDP) - return true; - return (type == DRM_MODE_CONNECTOR_DisplayPort); + ret = type == DRM_MODE_CONNECTOR_eDP || + type == DRM_MODE_CONNECTOR_DisplayPort; + break; + case TRANS_DDI_MODE_SELECT_DP_MST: /* if the transcoder is in MST state then * connector isn't connected */ - return false; + ret = false; + break; case TRANS_DDI_MODE_SELECT_FDI: - return (type == DRM_MODE_CONNECTOR_VGA); + ret = type == DRM_MODE_CONNECTOR_VGA; + break; default: - return false; + ret = false; + break; } + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } bool intel_ddi_get_hw_state(struct intel_encoder *encoder, @@ -2015,15 +2028,18 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum intel_display_power_domain power_domain; u32 tmp; int i; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(DDI_BUF_CTL(port)); if (!(tmp & DDI_BUF_CTL_ENABLE)) - return false; + goto out; if (port == PORT_A) { tmp = I915_READ(TRANS_DDI_FUNC_CTL(TRANSCODER_EDP)); @@ -2041,25 +2057,32 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder, break; } - return true; - } else { - for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) { - tmp = I915_READ(TRANS_DDI_FUNC_CTL(i)); + ret = true; - if ((tmp & TRANS_DDI_PORT_MASK) - == TRANS_DDI_SELECT_PORT(port)) { - if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == TRANS_DDI_MODE_SELECT_DP_MST) - return false; + goto out; + } - *pipe = i; - return true; - } + for (i = TRANSCODER_A; i <= TRANSCODER_C; i++) { + tmp = I915_READ(TRANS_DDI_FUNC_CTL(i)); + + if ((tmp & TRANS_DDI_PORT_MASK) == TRANS_DDI_SELECT_PORT(port)) { + if ((tmp & TRANS_DDI_MODE_SELECT_MASK) == + TRANS_DDI_MODE_SELECT_DP_MST) + goto out; + + *pipe = i; + ret = true; + + goto out; } } DRM_DEBUG_KMS("No pipe for ddi port %c found\n", port_name(port)); - return false; +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } void intel_ddi_enable_pipe_clock(struct intel_crtc *intel_crtc) @@ -2508,12 +2531,14 @@ static bool hsw_ddi_wrpll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(WRPLL_CTL(pll->id)); hw_state->wrpll = val; + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & WRPLL_PLL_ENABLE; } @@ -2523,12 +2548,14 @@ static bool hsw_ddi_spll_get_hw_state(struct drm_i915_private *dev_priv, { uint32_t val; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; val = I915_READ(SPLL_CTL); hw_state->spll = val; + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + return val & SPLL_PLL_ENABLE; } @@ -2645,16 +2672,19 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, uint32_t val; unsigned int dpll; const struct skl_dpll_regs *regs = skl_dpll_regs; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; + ret = false; + /* DPLL0 is not part of the shared DPLLs, so pll->id is 0 for DPLL1 */ dpll = pll->id + 1; val = I915_READ(regs[pll->id].ctl); if (!(val & LCPLL_PLL_ENABLE)) - return false; + goto out; val = I915_READ(DPLL_CTRL1); hw_state->ctrl1 = (val >> (dpll * 6)) & 0x3f; @@ -2664,8 +2694,12 @@ static bool skl_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, hw_state->cfgcr1 = I915_READ(regs[pll->id].cfgcr1); hw_state->cfgcr2 = I915_READ(regs[pll->id].cfgcr2); } + ret = true; - return true; +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + + return ret; } static void skl_shared_dplls_init(struct drm_i915_private *dev_priv) @@ -2932,13 +2966,16 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, { enum port port = (enum port)pll->id; /* 1:1 port->PLL mapping */ uint32_t val; + bool ret; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PLLS)) + if (!intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_PLLS)) return false; + ret = false; + val = I915_READ(BXT_PORT_PLL_ENABLE(port)); if (!(val & PORT_PLL_ENABLE)) - return false; + goto out; hw_state->ebb0 = I915_READ(BXT_PORT_PLL_EBB_0(port)); hw_state->ebb0 &= PORT_PLL_P1_MASK | PORT_PLL_P2_MASK; @@ -2985,7 +3022,12 @@ static bool bxt_ddi_pll_get_hw_state(struct drm_i915_private *dev_priv, I915_READ(BXT_PORT_PCS_DW12_LN23(port))); hw_state->pcsdw12 &= LANE_STAGGER_MASK | LANESTAGGER_STRAP_OVRD; - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, POWER_DOMAIN_PLLS); + + return ret; } static void bxt_shared_dplls_init(struct drm_i915_private *dev_priv) @@ -3120,11 +3162,15 @@ bool intel_ddi_is_audio_enabled(struct drm_i915_private *dev_priv, { u32 temp; - if (intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { + if (intel_display_power_get_if_enabled(dev_priv, POWER_DOMAIN_AUDIO)) { temp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD); + + intel_display_power_put(dev_priv, POWER_DOMAIN_AUDIO); + if (temp & AUDIO_OUTPUT_ENABLE(intel_crtc->pipe)) return true; } + return false; } From 02f9f5e62a9b0a1af2edd4fbd8194c9c5475459b Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:17 +0200 Subject: [PATCH 390/489] drm/i915: Ensure the HW is powered when accessing the CRC HW block The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. While at it also add the missing reference around the HW access in i915_interrupt_info(). v2: - update the commit message mentioning that this also fixes the HW access in the interrupt info debugfs entry (Daniel) Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-9-git-send-email-imre.deak@intel.com (cherry picked from commit e129649b7a3e1d50d196e159492496777769437e) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_debugfs.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c index 0fc38bb7276c..cf39ed3133d6 100644 --- a/drivers/gpu/drm/i915/i915_debugfs.c +++ b/drivers/gpu/drm/i915/i915_debugfs.c @@ -825,8 +825,11 @@ static int i915_interrupt_info(struct seq_file *m, void *data) } for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, - POWER_DOMAIN_PIPE(pipe))) { + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, + power_domain)) { seq_printf(m, "Pipe %c power disabled\n", pipe_name(pipe)); continue; @@ -840,6 +843,8 @@ static int i915_interrupt_info(struct seq_file *m, void *data) seq_printf(m, "Pipe %c IER:\t%08x\n", pipe_name(pipe), I915_READ(GEN8_DE_PIPE_IER(pipe))); + + intel_display_power_put(dev_priv, power_domain); } seq_printf(m, "Display Engine port interrupt mask:\t%08x\n", @@ -3985,6 +3990,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe]; struct intel_crtc *crtc = to_intel_crtc(intel_get_crtc_for_pipe(dev, pipe)); + enum intel_display_power_domain power_domain; u32 val = 0; /* shut up gcc */ int ret; @@ -3995,7 +4001,8 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, if (pipe_crc->source && source) return -EINVAL; - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) { + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) { DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n"); return -EIO; } @@ -4012,7 +4019,7 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, ret = ivb_pipe_crc_ctl_reg(dev, pipe, &source, &val); if (ret != 0) - return ret; + goto out; /* none -> real source transition */ if (source) { @@ -4024,8 +4031,10 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR, sizeof(pipe_crc->entries[0]), GFP_KERNEL); - if (!entries) - return -ENOMEM; + if (!entries) { + ret = -ENOMEM; + goto out; + } /* * When IPS gets enabled, the pipe CRC changes. Since IPS gets @@ -4081,7 +4090,12 @@ static int pipe_crc_set_source(struct drm_device *dev, enum pipe pipe, hsw_enable_ips(crtc); } - return 0; + ret = 0; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } /* From b81b801f8675838d69d1062a47ca46530ca7217b Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:18 +0200 Subject: [PATCH 391/489] drm/i915/dp: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-10-git-send-email-imre.deak@intel.com (cherry picked from commit 6fa9a5ecf7a54450b255229ac1fc6df276cf0653) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_dp.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c index 1bbd67b046da..1d8de43bed56 100644 --- a/drivers/gpu/drm/i915/intel_dp.c +++ b/drivers/gpu/drm/i915/intel_dp.c @@ -2362,15 +2362,18 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, struct drm_i915_private *dev_priv = dev->dev_private; enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(intel_dp->output_reg); if (!(tmp & DP_PORT_EN)) - return false; + goto out; if (IS_GEN7(dev) && port == PORT_A) { *pipe = PORT_TO_PIPE_CPT(tmp); @@ -2381,7 +2384,9 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, u32 trans_dp = I915_READ(TRANS_DP_CTL(p)); if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) { *pipe = p; - return true; + ret = true; + + goto out; } } @@ -2393,7 +2398,12 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder, *pipe = PORT_TO_PIPE(tmp); } - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_dp_get_config(struct intel_encoder *encoder, From fe97fd7eb87255883ae1da2d726baaae2b50e80d Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:19 +0200 Subject: [PATCH 392/489] drm/i915/dsi: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-11-git-send-email-imre.deak@intel.com (cherry picked from commit 3f3f42b887fbffc3353e44ef9f32456c19ae4280) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_dsi.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c index 44742fa2f616..0193c62a53ef 100644 --- a/drivers/gpu/drm/i915/intel_dsi.c +++ b/drivers/gpu/drm/i915/intel_dsi.c @@ -664,13 +664,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, struct drm_device *dev = encoder->base.dev; enum intel_display_power_domain power_domain; enum port port; + bool ret; DRM_DEBUG_KMS("\n"); power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + /* XXX: this only works for one DSI output */ for_each_dsi_port(port, intel_dsi->ports) { i915_reg_t ctrl_reg = IS_BROXTON(dev) ? @@ -691,12 +694,16 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder, if (dpi_enabled || (func & CMD_MODE_DATA_WIDTH_MASK)) { if (I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY) { *pipe = port == PORT_A ? PIPE_A : PIPE_B; - return true; + ret = true; + + goto out; } } } +out: + intel_display_power_put(dev_priv, power_domain); - return false; + return ret; } static void intel_dsi_get_config(struct intel_encoder *encoder, From 31feb61a688bd4b1c1cb66cc24d931ee77826d93 Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:20 +0200 Subject: [PATCH 393/489] drm/i915/hdmi: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-12-git-send-email-imre.deak@intel.com (cherry picked from commit 5b0921748c0b1d0362bbfa802dc25a5c23de7e76) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_hdmi.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index 4a77639a489d..cb5d1b15755c 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -880,15 +880,18 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(intel_hdmi->hdmi_reg); if (!(tmp & SDVO_ENABLE)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); @@ -897,7 +900,12 @@ static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder, else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_hdmi_get_config(struct intel_encoder *encoder, From 380bdff2d05b498227c80caedd125e8cfcdba00d Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Fri, 12 Feb 2016 18:55:21 +0200 Subject: [PATCH 394/489] drm/i915/lvds: Ensure the HW is powered during HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Signed-off-by: Imre Deak Reviewed-by: Daniel Vetter Link: http://patchwork.freedesktop.org/patch/msgid/1455296121-4742-13-git-send-email-imre.deak@intel.com (cherry picked from commit ecb2448218acf23c401434c26be256147833b221) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_lvds.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 0da0240caf81..bc04d8d29acb 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -75,22 +75,30 @@ static bool intel_lvds_get_hw_state(struct intel_encoder *encoder, struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base); enum intel_display_power_domain power_domain; u32 tmp; + bool ret; power_domain = intel_display_port_power_domain(encoder); - if (!intel_display_power_is_enabled(dev_priv, power_domain)) + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) return false; + ret = false; + tmp = I915_READ(lvds_encoder->reg); if (!(tmp & LVDS_PORT_EN)) - return false; + goto out; if (HAS_PCH_CPT(dev)) *pipe = PORT_TO_PIPE_CPT(tmp); else *pipe = PORT_TO_PIPE(tmp); - return true; + ret = true; + +out: + intel_display_power_put(dev_priv, power_domain); + + return ret; } static void intel_lvds_get_config(struct intel_encoder *encoder, From 53188eb40121a135892881c5f61e41efce60b00a Mon Sep 17 00:00:00 2001 From: Imre Deak Date: Tue, 16 Feb 2016 18:56:46 +0200 Subject: [PATCH 395/489] drm/i915/skl: Ensure HW is powered during DDB HW state readout The assumption when adding the intel_display_power_is_enabled() checks was that if it returns success the power can't be turned off afterwards during the HW access, which is guaranteed by modeset locks. This isn't always true, so make sure we hold a dedicated reference for the time of the access. Spotted-by: Mika Kuoppala Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93441 CC: Chris Wilson Signed-off-by: Imre Deak Reviewed-by: Mika Kuoppala Link: http://patchwork.freedesktop.org/patch/msgid/1455719489-3008-1-git-send-email-imre.deak@intel.com (cherry picked from commit 4d800030238878c1a98d1d3a37a3d673eea661ce) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_pm.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index a234687792f0..b28c29f20e75 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -2829,7 +2829,10 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, memset(ddb, 0, sizeof(*ddb)); for_each_pipe(dev_priv, pipe) { - if (!intel_display_power_is_enabled(dev_priv, POWER_DOMAIN_PIPE(pipe))) + enum intel_display_power_domain power_domain; + + power_domain = POWER_DOMAIN_PIPE(pipe); + if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) continue; for_each_plane(dev_priv, pipe, plane) { @@ -2841,6 +2844,8 @@ void skl_ddb_get_hw_state(struct drm_i915_private *dev_priv, val = I915_READ(CUR_BUF_CFG(pipe)); skl_ddb_entry_init_from_hw(&ddb->plane[pipe][PLANE_CURSOR], val); + + intel_display_power_put(dev_priv, power_domain); } } From 7e31a0159461818a1bda49662921b98a29c1187b Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Mon, 22 Feb 2016 15:18:13 +0100 Subject: [PATCH 396/489] ALSA: hda - Apply clock gate workaround to Skylake, too Some Skylake machines show the codec probe errors in certain situations, e.g. HP Z240 desktop fails to probe the onboard Realtek codec at reloading the snd-hda-intel module like: snd_hda_intel 0000:00:1f.3: spurious response 0x200:0x2, last cmd=0x000000 snd_hda_intel 0000:00:1f.3: azx_get_response timeout, switching to polling mode: lastcmd=0x000f0000 snd_hda_intel 0000:00:1f.3: No response from codec, disabling MSI: last cmd=0x000f0000 snd_hda_intel 0000:00:1f.3: Codec #0 probe error; disabling it... hdaudio hdaudioC0D2: no AFG or MFG node found snd_hda_intel 0000:00:1f.3: no codecs initialized Also, HP G470 G3 suffers from the similar problem, as reported in bugzilla below. On this machine, the codec probe error appears even at a fresh boot. As Libin suggested, the same workaround used for Broxton in the commit [6639484ddaf6: ALSA: hda - disable dynamic clock gating on Broxton before reset] can be applied for Skylake in order to fix this problem. The Intel HW team also confirmed that this is needed for SKL. This patch makes the workaround applied to both SKL and BXT platforms. The referred macros are moved and one superfluous macro (IS_BROXTON()) is another one (IS_BXT()) as well. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=112731 Suggested-by: Libin Yang Cc: # v4.4+ Signed-off-by: Takashi Iwai --- sound/pci/hda/hda_intel.c | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index ce6b97f31390..e5240cb3749f 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -363,7 +363,10 @@ enum { ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c)) -#define IS_BROXTON(pci) ((pci)->device == 0x5a98) +#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) +#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) +#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) +#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", @@ -540,13 +543,13 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); - if (IS_BROXTON(pci)) { + if (IS_SKL_PLUS(pci)) { pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); val = val & ~INTEL_HDA_CGCTL_MISCBDCGE; pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); } azx_init_chip(chip, full_reset); - if (IS_BROXTON(pci)) { + if (IS_SKL_PLUS(pci)) { pci_read_config_dword(pci, INTEL_HDA_CGCTL, &val); val = val | INTEL_HDA_CGCTL_MISCBDCGE; pci_write_config_dword(pci, INTEL_HDA_CGCTL, val); @@ -555,7 +558,7 @@ static void hda_intel_init_chip(struct azx *chip, bool full_reset) snd_hdac_set_codec_wakeup(bus, false); /* reduce dma latency to avoid noise */ - if (IS_BROXTON(pci)) + if (IS_BXT(pci)) bxt_reduce_dma_latency(chip); } @@ -977,11 +980,6 @@ static int azx_resume(struct device *dev) /* put codec down to D3 at hibernation for Intel SKL+; * otherwise BIOS may still access the codec and screw up the driver */ -#define IS_SKL(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0xa170) -#define IS_SKL_LP(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x9d70) -#define IS_BXT(pci) ((pci)->vendor == 0x8086 && (pci)->device == 0x5a98) -#define IS_SKL_PLUS(pci) (IS_SKL(pci) || IS_SKL_LP(pci) || IS_BXT(pci)) - static int azx_freeze_noirq(struct device *dev) { struct pci_dev *pci = to_pci_dev(dev); From 04ab3b7622a618ea081d17427c15a292710b40cb Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 18 Feb 2016 11:10:09 -0500 Subject: [PATCH 397/489] drm/amdgpu/gfx8: fix priv reg interrupt enable MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Looks like a copy/paste typo. Reviewed-by: Christian König Noticed-by: David Panariti Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c index 8f8ec37ecd88..1c40bd90afbb 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c @@ -4995,7 +4995,7 @@ static int gfx_v8_0_set_priv_reg_fault_state(struct amdgpu_device *adev, case AMDGPU_IRQ_STATE_ENABLE: cp_int_cntl = RREG32(mmCP_INT_CNTL_RING0); cp_int_cntl = REG_SET_FIELD(cp_int_cntl, CP_INT_CNTL_RING0, - PRIV_REG_INT_ENABLE, 0); + PRIV_REG_INT_ENABLE, 1); WREG32(mmCP_INT_CNTL_RING0, cp_int_cntl); break; default: From 10f950f640e689336af0a0d587a4b3c26a73cd44 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 15:18:45 -0500 Subject: [PATCH 398/489] drm/amdgpu: fix locking in force performance level MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Looks like a copy paste typo when we added powerplay support. Reviewed-by: Christian König Acked-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 7d8d84eaea4a..5ed5598997e9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -157,6 +157,7 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, mutex_lock(&adev->pm.mutex); if (adev->pm.dpm.thermal_active) { count = -EINVAL; + mutex_unlock(&adev->pm.mutex); goto fail; } ret = amdgpu_dpm_force_performance_level(adev, level); @@ -167,8 +168,6 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, mutex_unlock(&adev->pm.mutex); } fail: - mutex_unlock(&adev->pm.mutex); - return count; } From 0c67df48597f0e60eaf7f187ee38f6ccce56561e Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 15:30:15 -0500 Subject: [PATCH 399/489] drm/amdgpu/pm: add some checks for PX MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit I.e., doesn't make sense to change power states or check the temperature when the asic is powered off. Reviewed-by: Christian König Acked-by: Harry Wentland Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 5ed5598997e9..8de765dee3e7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -113,6 +113,10 @@ static ssize_t amdgpu_get_dpm_forced_performance_level(struct device *dev, struct drm_device *ddev = dev_get_drvdata(dev); struct amdgpu_device *adev = ddev->dev_private; + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return snprintf(buf, PAGE_SIZE, "off\n"); + if (adev->pp_enabled) { enum amd_dpm_forced_level level; @@ -140,6 +144,11 @@ static ssize_t amdgpu_set_dpm_forced_performance_level(struct device *dev, enum amdgpu_dpm_forced_level level; int ret = 0; + /* Can't force performance level when the card is off */ + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (strncmp("low", buf, strlen("low")) == 0) { level = AMDGPU_DPM_FORCED_LEVEL_LOW; } else if (strncmp("high", buf, strlen("high")) == 0) { @@ -181,8 +190,14 @@ static ssize_t amdgpu_hwmon_show_temp(struct device *dev, char *buf) { struct amdgpu_device *adev = dev_get_drvdata(dev); + struct drm_device *ddev = adev->ddev; int temp; + /* Can't get temperature when the card is off */ + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) + return -EINVAL; + if (!adev->pp_enabled && !adev->pm.funcs->get_temperature) temp = 0; else @@ -846,12 +861,16 @@ static int amdgpu_debugfs_pm_info(struct seq_file *m, void *data) struct drm_info_node *node = (struct drm_info_node *) m->private; struct drm_device *dev = node->minor->dev; struct amdgpu_device *adev = dev->dev_private; + struct drm_device *ddev = adev->ddev; if (!adev->pm.dpm_enabled) { seq_printf(m, "dpm not enabled\n"); return 0; } - if (adev->pp_enabled) { + if ((adev->flags & AMD_IS_PX) && + (ddev->switch_power_state != DRM_SWITCH_POWER_ON)) { + seq_printf(m, "PX asic powered off\n"); + } else if (adev->pp_enabled) { amdgpu_dpm_debugfs_print_current_performance_level(adev, m); } else { mutex_lock(&adev->pm.mutex); From 8e7cedc6f7fe762ffe6e348502be34b11fa79298 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 17:55:31 -0500 Subject: [PATCH 400/489] drm/amdgpu/pm: adjust display configuration after powerstate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit set_power_state defaults to no displays, so we need to update the display configuration after setting up the powerstate on the first call. In most cases this is not an issue since ends up getting called multiple times at any given modeset and the proper order is achieved in the display changed handling at the top of the function. Reviewed-by: Christian König Acked-by: Jordan Lazare Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 8de765dee3e7..66855b62a603 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -648,8 +648,6 @@ force: /* update display watermarks based on new power state */ amdgpu_display_bandwidth_update(adev); - /* update displays */ - amdgpu_dpm_display_configuration_changed(adev); adev->pm.dpm.current_active_crtcs = adev->pm.dpm.new_active_crtcs; adev->pm.dpm.current_active_crtc_count = adev->pm.dpm.new_active_crtc_count; @@ -669,6 +667,9 @@ force: amdgpu_dpm_post_set_power_state(adev); + /* update displays */ + amdgpu_dpm_display_configuration_changed(adev); + if (adev->pm.funcs->force_performance_level) { if (adev->pm.dpm.thermal_active) { enum amdgpu_dpm_forced_level level = adev->pm.dpm.forced_level; From 39d4275058baf53e89203407bf3841ff2c74fa32 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Fri, 19 Feb 2016 18:05:10 -0500 Subject: [PATCH 401/489] drm/radeon/pm: adjust display configuration after powerstate MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit set_power_state defaults to no displays, so we need to update the display configuration after setting up the powerstate on the first call. In most cases this is not an issue since ends up getting called multiple times at any given modeset and the proper order is achieved in the display changed handling at the top of the function. Reviewed-by: Christian König Acked-by: Jordan Lazare Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/radeon/radeon_pm.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c index 248c5a9fb0b6..ca3be90a3bb4 100644 --- a/drivers/gpu/drm/radeon/radeon_pm.c +++ b/drivers/gpu/drm/radeon/radeon_pm.c @@ -1079,8 +1079,6 @@ force: /* update display watermarks based on new power state */ radeon_bandwidth_update(rdev); - /* update displays */ - radeon_dpm_display_configuration_changed(rdev); rdev->pm.dpm.current_active_crtcs = rdev->pm.dpm.new_active_crtcs; rdev->pm.dpm.current_active_crtc_count = rdev->pm.dpm.new_active_crtc_count; @@ -1101,6 +1099,9 @@ force: radeon_dpm_post_set_power_state(rdev); + /* update displays */ + radeon_dpm_display_configuration_changed(rdev); + if (rdev->asic->dpm.force_performance_level) { if (rdev->pm.dpm.thermal_active) { enum radeon_dpm_forced_level level = rdev->pm.dpm.forced_level; From 9b6f20984c5402af06e13cde64b5fe7c31853d1a Mon Sep 17 00:00:00 2001 From: Patrik Jakobsson Date: Thu, 18 Feb 2016 17:21:11 +0200 Subject: [PATCH 402/489] drm/i915/gen9: Check for DC state mismatch The DMC can incorrectly run off and allow DC states on it's own. We don't know the root-cause for this yet but this patch makes it more visible. Reviewed-by: Mika Kuoppala Signed-off-by: Patrik Jakobsson Signed-off-by: Imre Deak Link: http://patchwork.freedesktop.org/patch/msgid/1455808874-22089-2-git-send-email-mika.kuoppala@intel.com (cherry picked from commit 832dba889e27487c3087149f1039acc3feb89003) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/i915_drv.h | 1 + drivers/gpu/drm/i915/intel_csr.c | 2 ++ drivers/gpu/drm/i915/intel_runtime_pm.c | 8 ++++++++ 3 files changed, 11 insertions(+) diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index e7cd311e9fbb..b0847b915545 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -751,6 +751,7 @@ struct intel_csr { uint32_t mmio_count; i915_reg_t mmioaddr[8]; uint32_t mmiodata[8]; + uint32_t dc_state; }; #define DEV_INFO_FOR_EACH_FLAG(func, sep) \ diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c index 9bb63a85997a..647d85e77c2f 100644 --- a/drivers/gpu/drm/i915/intel_csr.c +++ b/drivers/gpu/drm/i915/intel_csr.c @@ -240,6 +240,8 @@ void intel_csr_load_program(struct drm_i915_private *dev_priv) I915_WRITE(dev_priv->csr.mmioaddr[i], dev_priv->csr.mmiodata[i]); } + + dev_priv->csr.dc_state = 0; } static uint32_t *parse_csr_fw(struct drm_i915_private *dev_priv, diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 89dcc99ac3ca..19e6ff64ce9d 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -494,10 +494,18 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) val = I915_READ(DC_STATE_EN); DRM_DEBUG_KMS("Setting DC state from %02x to %02x\n", val & mask, state); + + /* Check if DMC is ignoring our DC state requests */ + if ((val & mask) != dev_priv->csr.dc_state) + DRM_ERROR("DC state mismatch (0x%x -> 0x%x)\n", + dev_priv->csr.dc_state, val & mask); + val &= ~mask; val |= state; I915_WRITE(DC_STATE_EN, val); POSTING_READ(DC_STATE_EN); + + dev_priv->csr.dc_state = val & mask; } void bxt_enable_dc9(struct drm_i915_private *dev_priv) From 9b18572e83bfd5378b3fcff3acf123f7bddf558a Mon Sep 17 00:00:00 2001 From: Mika Kuoppala Date: Thu, 18 Feb 2016 17:58:09 +0200 Subject: [PATCH 403/489] drm/i915/gen9: Verify and enforce dc6 state writes It has been observed that sometimes disabling the dc6 fails and dc6 state pops back up, brief moment after disabling. This has to be dmc save/restore timing issue or other bug in the way dc states are handled. Try to work around this issue as we don't have firmware fix yet available. Verify that the value we wrote for the dmc sticks, and also enforce it by rewriting it, if it didn't. v2: Zero rereads on rewrite for extra paranoia (Imre) Testcase: kms_flip/basic-flip-vs-dpms References: https://bugs.freedesktop.org/show_bug.cgi?id=93768 Cc: Patrik Jakobsson Cc: Rodrigo Vivi Cc: Imre Deak Signed-off-by: Mika Kuoppala Reviewed-by: Imre Deak Signed-off-by: Imre Deak Link: http://patchwork.freedesktop.org/patch/msgid/1455811089-27884-1-git-send-email-mika.kuoppala@intel.com (cherry picked from commit 779cb5d3ddd72950ec726f86e38f7575c7fbdd4c) Signed-off-by: Jani Nikula --- drivers/gpu/drm/i915/intel_runtime_pm.c | 41 +++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c index 19e6ff64ce9d..678ed3475d7e 100644 --- a/drivers/gpu/drm/i915/intel_runtime_pm.c +++ b/drivers/gpu/drm/i915/intel_runtime_pm.c @@ -470,6 +470,43 @@ static void gen9_set_dc_state_debugmask_memory_up( } } +static void gen9_write_dc_state(struct drm_i915_private *dev_priv, + u32 state) +{ + int rewrites = 0; + int rereads = 0; + u32 v; + + I915_WRITE(DC_STATE_EN, state); + + /* It has been observed that disabling the dc6 state sometimes + * doesn't stick and dmc keeps returning old value. Make sure + * the write really sticks enough times and also force rewrite until + * we are confident that state is exactly what we want. + */ + do { + v = I915_READ(DC_STATE_EN); + + if (v != state) { + I915_WRITE(DC_STATE_EN, state); + rewrites++; + rereads = 0; + } else if (rereads++ > 5) { + break; + } + + } while (rewrites < 100); + + if (v != state) + DRM_ERROR("Writing dc state to 0x%x failed, now 0x%x\n", + state, v); + + /* Most of the times we need one retry, avoid spam */ + if (rewrites > 1) + DRM_DEBUG_KMS("Rewrote dc state to 0x%x %d times\n", + state, rewrites); +} + static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) { uint32_t val; @@ -502,8 +539,8 @@ static void gen9_set_dc_state(struct drm_i915_private *dev_priv, uint32_t state) val &= ~mask; val |= state; - I915_WRITE(DC_STATE_EN, val); - POSTING_READ(DC_STATE_EN); + + gen9_write_dc_state(dev_priv, val); dev_priv->csr.dc_state = val & mask; } From 3f315c5b850fa7aff73f50de8e316b98f611a32b Mon Sep 17 00:00:00 2001 From: Ivaylo Dimitrov Date: Fri, 5 Feb 2016 16:37:08 +0200 Subject: [PATCH 404/489] ARM: OMAP2+: Fix onenand initialization to avoid filesystem corruption Commit e7b11dc7b77b ("ARM: OMAP2+: Fix onenand rate detection to avoid filesystem corruption") partially fixed onenand configuration when GPMC module is reset. Finish the job by also providing the correct values in ONENAND_REG_SYS_CFG1 register. Fixes: e7b11dc7b77b ("ARM: OMAP2+: Fix onenand rate detection to avoid filesystem corruption") Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Ivaylo Dimitrov Tested-by: Aaro Koskinen Signed-off-by: Tony Lindgren --- arch/arm/mach-omap2/gpmc-onenand.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/arm/mach-omap2/gpmc-onenand.c b/arch/arm/mach-omap2/gpmc-onenand.c index 7b76ce01c21d..8633c703546a 100644 --- a/arch/arm/mach-omap2/gpmc-onenand.c +++ b/arch/arm/mach-omap2/gpmc-onenand.c @@ -101,10 +101,8 @@ static void omap2_onenand_set_async_mode(void __iomem *onenand_base) static void set_onenand_cfg(void __iomem *onenand_base) { - u32 reg; + u32 reg = ONENAND_SYS_CFG1_RDY | ONENAND_SYS_CFG1_INT; - reg = readw(onenand_base + ONENAND_REG_SYS_CFG1); - reg &= ~((0x7 << ONENAND_SYS_CFG1_BRL_SHIFT) | (0x7 << 9)); reg |= (latency << ONENAND_SYS_CFG1_BRL_SHIFT) | ONENAND_SYS_CFG1_BL_16; if (onenand_flags & ONENAND_FLAG_SYNCREAD) @@ -123,6 +121,7 @@ static void set_onenand_cfg(void __iomem *onenand_base) reg |= ONENAND_SYS_CFG1_VHF; else reg &= ~ONENAND_SYS_CFG1_VHF; + writew(reg, onenand_base + ONENAND_REG_SYS_CFG1); } @@ -289,6 +288,7 @@ static int omap2_onenand_setup_async(void __iomem *onenand_base) } } + onenand_async.sync_write = true; omap2_onenand_calc_async_timings(&t); ret = gpmc_cs_program_settings(gpmc_onenand_data->cs, &onenand_async); From a0d54c3899aaeb047969d9479263c6bcf385c331 Mon Sep 17 00:00:00 2001 From: Tero Kristo Date: Sat, 20 Feb 2016 13:12:57 +0200 Subject: [PATCH 405/489] clk: ti: omap3+: dpll: use non-locking version of clk_get_rate As the code in this file is being executed within irq context in some cases, we must avoid the clk_get_rate which uses mutex internally. Switch the code to use clk_hw_get_rate instead which is non-locking. This fixes an issue where PM runtime will hang the system if enabled with a serial console before a suspend-resume cycle. Signed-off-by: Tero Kristo Tested-by: Tony Lindgren Fixes: a53ad8ef3dcc ("clk: ti: Convert to clk_hw based provider APIs") Signed-off-by: Stephen Boyd --- drivers/clk/ti/dpll3xxx.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/clk/ti/dpll3xxx.c b/drivers/clk/ti/dpll3xxx.c index 1c300388782b..cc739291a3ce 100644 --- a/drivers/clk/ti/dpll3xxx.c +++ b/drivers/clk/ti/dpll3xxx.c @@ -460,7 +460,8 @@ int omap3_noncore_dpll_enable(struct clk_hw *hw) parent = clk_hw_get_parent(hw); - if (clk_hw_get_rate(hw) == clk_get_rate(dd->clk_bypass)) { + if (clk_hw_get_rate(hw) == + clk_hw_get_rate(__clk_get_hw(dd->clk_bypass))) { WARN_ON(parent != __clk_get_hw(dd->clk_bypass)); r = _omap3_noncore_dpll_bypass(clk); } else { From 2454dfea0aef8a883d4302c38124edb373d47a25 Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 22 Feb 2016 17:34:59 -0500 Subject: [PATCH 406/489] NFSv4.x/pnfs: Fix a race between layoutget and pnfs_destroy_layout If the server reboots while there is a layoutget outstanding, then the call to pnfs_choose_layoutget_stateid() will fail with an EAGAIN error, which causes an infinite loop in send_layoutget(). The reason why we never break out of the loop is that the layout 'plh_block_lgets' field is never cleared. Fix is to replace plh_block_lgets with NFS_LAYOUT_INVALID_STID, which can be reset after a new layoutget. Fixes: ab7d763e477c5 ("pNFS: Ensure nfs4_layoutget_prepare returns...") Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5064f23ca8cc..8a41538f1155 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -252,6 +252,27 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) } } +/* + * Mark a pnfs_layout_hdr and all associated layout segments as invalid + * + * In order to continue using the pnfs_layout_hdr, a full recovery + * is required. + * Note that caller must hold inode->i_lock. + */ +static void +pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, + struct list_head *lseg_list) +{ + struct pnfs_layout_range range = { + .iomode = IOMODE_ANY, + .offset = 0, + .length = NFS4_MAX_UINT64, + }; + + set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); + pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); +} + static int pnfs_iomode_to_fail_bit(u32 iomode) { @@ -554,9 +575,8 @@ pnfs_destroy_layout(struct nfs_inode *nfsi) spin_lock(&nfsi->vfs_inode.i_lock); lo = nfsi->layout; if (lo) { - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL); pnfs_get_layout_hdr(lo); + pnfs_mark_layout_stateid_invalid(lo, &tmp_list); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED); pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED); spin_unlock(&nfsi->vfs_inode.i_lock); From 9fd4b9fc7695a4da1363a0b439853f88fb6a034f Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Mon, 22 Feb 2016 17:46:34 -0500 Subject: [PATCH 407/489] NFSv4.x/pnfs: Fix a race between layoutget and bulk recalls Replace another case where the layout 'plh_block_lgets' can trigger infinite loops in send_layoutget(). Signed-off-by: Trond Myklebust --- fs/nfs/pnfs.c | 17 ++++++----------- 1 file changed, 6 insertions(+), 11 deletions(-) diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 8a41538f1155..2fa483e6dbe2 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -259,7 +259,7 @@ pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo) * is required. * Note that caller must hold inode->i_lock. */ -static void +static int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list) { @@ -270,7 +270,7 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, }; set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags); - pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); + return pnfs_mark_matching_lsegs_invalid(lo, lseg_list, &range); } static int @@ -637,11 +637,6 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, { struct pnfs_layout_hdr *lo; struct inode *inode; - struct pnfs_layout_range range = { - .iomode = IOMODE_ANY, - .offset = 0, - .length = NFS4_MAX_UINT64, - }; LIST_HEAD(lseg_list); int ret = 0; @@ -656,11 +651,11 @@ pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list, spin_lock(&inode->i_lock); list_del_init(&lo->plh_bulk_destroy); - lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */ - if (is_bulk_recall) - set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); - if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range)) + if (pnfs_mark_layout_stateid_invalid(lo, &lseg_list)) { + if (is_bulk_recall) + set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags); ret = -EAGAIN; + } spin_unlock(&inode->i_lock); pnfs_free_lseg_list(&lseg_list); /* Free all lsegs that are attached to commit buckets */ From dbb0c7c430ddbe4299f3580baec0e2503f6f5a93 Mon Sep 17 00:00:00 2001 From: Tomeu Vizoso Date: Thu, 21 Jan 2016 08:52:26 +0100 Subject: [PATCH 408/489] PM / devfreq: tegra: Set freq in rate callback As per the documentation of the devfreq_dev_profile.target callback, set the freq argument to the new frequency before returning. This caused endless messages like this after recent changes in the core: devfreq 6000c800.actmon: Couldn't update frequency transition information. Signed-off-by: Tomeu Vizoso Reported-by: Tyler Baker Tested-by: Thierry Reding Acked-by: Thierry Reding Signed-off-by: MyungJoo Ham --- drivers/devfreq/tegra-devfreq.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c index 848b93ee930f..fe9dce0245bf 100644 --- a/drivers/devfreq/tegra-devfreq.c +++ b/drivers/devfreq/tegra-devfreq.c @@ -500,6 +500,8 @@ static int tegra_devfreq_target(struct device *dev, unsigned long *freq, clk_set_min_rate(tegra->emc_clock, rate); clk_set_rate(tegra->emc_clock, 0); + *freq = rate; + return 0; } From dd71a17b1193dd4a4c35ecd0ba227aac3d110836 Mon Sep 17 00:00:00 2001 From: Bryan O'Donoghue Date: Tue, 23 Feb 2016 01:29:58 +0000 Subject: [PATCH 409/489] x86/platform/intel/quark: Change the kernel's IMR lock bit to false Currently when setting up an IMR around the kernel's .text section we lock that IMR, preventing further modification. While superficially this appears to be the right thing to do, in fact this doesn't account for a legitimate change in the memory map such as when executing a new kernel via kexec. In such a scenario a second kernel can have a different size and location to it's predecessor and can view some of the memory occupied by it's predecessor as legitimately usable DMA RAM. If this RAM were then subsequently allocated to DMA agents within the system it could conceivably trigger an IMR violation. This patch fixes the this potential situation by keeping the kernel's .text section IMR lock bit false by default. Suggested-by: Ingo Molnar Reported-by: Andy Shevchenko Signed-off-by: Bryan O'Donoghue Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: boon.leong.ong@intel.com Cc: paul.gortmaker@windriver.com Link: http://lkml.kernel.org/r/1456190999-12685-2-git-send-email-pure.logic@nexus-software.ie Signed-off-by: Ingo Molnar --- arch/x86/platform/intel-quark/imr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c index c61b6c332e97..bfadcd0f4944 100644 --- a/arch/x86/platform/intel-quark/imr.c +++ b/arch/x86/platform/intel-quark/imr.c @@ -592,14 +592,14 @@ static void __init imr_fixup_memmap(struct imr_device *idev) end = (unsigned long)__end_rodata - 1; /* - * Setup a locked IMR around the physical extent of the kernel + * Setup an unlocked IMR around the physical extent of the kernel * from the beginning of the .text secton to the end of the * .rodata section as one physically contiguous block. * * We don't round up @size since it is already PAGE_SIZE aligned. * See vmlinux.lds.S for details. */ - ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true); + ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false); if (ret < 0) { pr_err("unable to setup IMR for kernel: %zu KiB (%lx - %lx)\n", size / 1024, start, end); From 31b994a4986dcdd664c597afcef2c0918763019a Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Mon, 8 Feb 2016 13:42:14 +0100 Subject: [PATCH 410/489] usb: gadget: remove driver from pending list on probe error Retry gadget probe only if the probe result is -EPROBE_DEFER, not on every probe error. Signed-off-by: Marek Szyprowski Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/udc-core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c index fd73a3ea07c2..b86a6f03592e 100644 --- a/drivers/usb/gadget/udc/udc-core.c +++ b/drivers/usb/gadget/udc/udc-core.c @@ -413,9 +413,10 @@ int usb_add_gadget_udc_release(struct device *parent, struct usb_gadget *gadget, if (!driver->udc_name || strcmp(driver->udc_name, dev_name(&udc->dev)) == 0) { ret = udc_bind_to_driver(udc, driver); + if (ret != -EPROBE_DEFER) + list_del(&driver->pending); if (ret) goto err4; - list_del(&driver->pending); break; } } From 7b0a271d5cadf5fbb5a9c7cb868776af2a2c248c Mon Sep 17 00:00:00 2001 From: Marek Szyprowski Date: Thu, 18 Feb 2016 08:59:26 +0100 Subject: [PATCH 411/489] usb: gadget: gadgetfs: unregister gadget only if it got successfully registered Gadgetfs driver called usb_gadget_unregister_driver unconditionally, even if it didn't register it earlier due to other failures. This patch fixes this. Reported-by: Vegard Nossum Signed-off-by: Marek Szyprowski Tested-by: Vegard Nossum Signed-off-by: Felipe Balbi --- drivers/usb/gadget/legacy/inode.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c index 7e179f81d05c..87fb0fd6aaab 100644 --- a/drivers/usb/gadget/legacy/inode.c +++ b/drivers/usb/gadget/legacy/inode.c @@ -130,7 +130,8 @@ struct dev_data { setup_can_stall : 1, setup_out_ready : 1, setup_out_error : 1, - setup_abort : 1; + setup_abort : 1, + gadget_registered : 1; unsigned setup_wLength; /* the rest is basically write-once */ @@ -1179,7 +1180,8 @@ dev_release (struct inode *inode, struct file *fd) /* closing ep0 === shutdown all */ - usb_gadget_unregister_driver (&gadgetfs_driver); + if (dev->gadget_registered) + usb_gadget_unregister_driver (&gadgetfs_driver); /* at this point "good" hardware has disconnected the * device from USB; the host won't see it any more. @@ -1847,6 +1849,7 @@ dev_config (struct file *fd, const char __user *buf, size_t len, loff_t *ptr) * kick in after the ep0 descriptor is closed. */ value = len; + dev->gadget_registered = true; } return value; From ca1c11894274c1687417945c034d6b8aee49f625 Mon Sep 17 00:00:00 2001 From: Simon Appleby Date: Tue, 9 Feb 2016 09:19:46 +0000 Subject: [PATCH 412/489] usb: gadget: net2280: fix endpoint max packet for super speed connections This patch fixes the register offset used for super-speed connection's max packet size. Without it using the 338x series of devices in enhanced mode will only allow full or high speed operation to function correctly. Signed-off-by: Simon Appleby Signed-off-by: Felipe Balbi --- drivers/usb/gadget/udc/net2280.h | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/drivers/usb/gadget/udc/net2280.h b/drivers/usb/gadget/udc/net2280.h index 4dff60d34f73..0d32052bf16f 100644 --- a/drivers/usb/gadget/udc/net2280.h +++ b/drivers/usb/gadget/udc/net2280.h @@ -369,9 +369,20 @@ static inline void set_max_speed(struct net2280_ep *ep, u32 max) static const u32 ep_enhanced[9] = { 0x10, 0x60, 0x30, 0x80, 0x50, 0x20, 0x70, 0x40, 0x90 }; - if (ep->dev->enhanced_mode) + if (ep->dev->enhanced_mode) { reg = ep_enhanced[ep->num]; - else{ + switch (ep->dev->gadget.speed) { + case USB_SPEED_SUPER: + reg += 2; + break; + case USB_SPEED_FULL: + reg += 1; + break; + case USB_SPEED_HIGH: + default: + break; + } + } else { reg = (ep->num + 1) * 0x10; if (ep->dev->gadget.speed != USB_SPEED_HIGH) reg += 1; From 8de4b3a3fcbc18e0aa62e9defe5c08821351be12 Mon Sep 17 00:00:00 2001 From: "Ivan T. Ivanov" Date: Fri, 5 Feb 2016 19:17:09 +0000 Subject: [PATCH 413/489] usb: phy: msm: Trigger USB state detection work in DRD mode When working in Dual Role Device mode, USB state machine is not kicked, when host or gadget drivers are loaded. Fix this be explicitly triggering state detection on client driver load. Issue is that if the board is booted without micro usb cable and usb device attached, kernel fails to populate the usb host and device. The reason for this is that the state machine worker logic only checks for USB_DR_MODE_PERIPHERAL and USB_DR_MODE_HOST modes to run worker thread. However if the phy is configured in OTG mode it would fail to run the state machine, resulting in failure to detect for very first time. This patch fixes the issue by removing the explicit checks. Issue is noticed on Qualcomm Dragon board DB410C. [srinivas.kandagatla@linaro.org: Added more details to log] Signed-off-by: Ivan T. Ivanov Signed-off-by: Srinivas Kandagatla Signed-off-by: Felipe Balbi --- drivers/usb/phy/phy-msm-usb.c | 20 ++++---------------- 1 file changed, 4 insertions(+), 16 deletions(-) diff --git a/drivers/usb/phy/phy-msm-usb.c b/drivers/usb/phy/phy-msm-usb.c index 970a30e155cb..72b387d592c2 100644 --- a/drivers/usb/phy/phy-msm-usb.c +++ b/drivers/usb/phy/phy-msm-usb.c @@ -757,14 +757,8 @@ static int msm_otg_set_host(struct usb_otg *otg, struct usb_bus *host) otg->host = host; dev_dbg(otg->usb_phy->dev, "host driver registered w/ tranceiver\n"); - /* - * Kick the state machine work, if peripheral is not supported - * or peripheral is already registered with us. - */ - if (motg->pdata->mode == USB_DR_MODE_HOST || otg->gadget) { - pm_runtime_get_sync(otg->usb_phy->dev); - schedule_work(&motg->sm_work); - } + pm_runtime_get_sync(otg->usb_phy->dev); + schedule_work(&motg->sm_work); return 0; } @@ -827,14 +821,8 @@ static int msm_otg_set_peripheral(struct usb_otg *otg, dev_dbg(otg->usb_phy->dev, "peripheral driver registered w/ tranceiver\n"); - /* - * Kick the state machine work, if host is not supported - * or host is already registered with us. - */ - if (motg->pdata->mode == USB_DR_MODE_PERIPHERAL || otg->host) { - pm_runtime_get_sync(otg->usb_phy->dev); - schedule_work(&motg->sm_work); - } + pm_runtime_get_sync(otg->usb_phy->dev); + schedule_work(&motg->sm_work); return 0; } From 4c2ba0c67394514f3f75c660c9f5d02e66a7efd4 Mon Sep 17 00:00:00 2001 From: Cristian Birsan Date: Fri, 19 Feb 2016 10:11:56 +0200 Subject: [PATCH 414/489] usb: musb: fix DMA for host mode Commit ac33cdb16681 ("usb: musb: Remove ifdefs for musb_host_rx in musb_host.c part5") introduces a problem setting DMA host mode. The musb_advance_schedule() is called immediately after receiving an endpoint RX interrupt without waiting for the DMA transfer to complete. As a consequence when the dma complete interrupt arrives the in_qh member of hw_ep is already null an the musb_host_rx() exits on !urb error case. Fix the done condition that advances the musb schedule. Signed-off-by: Cristian Birsan Signed-off-by: Joshua Henderson Tested-by: Ladislav Michl Signed-off-by: Felipe Balbi --- drivers/usb/musb/musb_host.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 79d081883628..58487a473521 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -2003,10 +2003,8 @@ void musb_host_rx(struct musb *musb, u8 epnum) qh->offset, urb->transfer_buffer_length); - done = musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, - urb, xfer_len, - iso_err); - if (done) + if (musb_rx_dma_in_inventra_cppi41(c, hw_ep, qh, urb, + xfer_len, iso_err)) goto finish; else dev_err(musb->controller, "error: rx_dma failed\n"); From 3b2435192fe917a826c91c8b34032428d6efdfc7 Mon Sep 17 00:00:00 2001 From: Felipe Balbi Date: Fri, 19 Feb 2016 11:04:55 +0200 Subject: [PATCH 415/489] MAINTAINERS: drop OMAP USB and MUSB maintainership Now that I have switched to another company, I won't be able to help by maintaining OMAP USB Support and/or the MUSB driver. OMAP USB Support is left Orphaned. MUSB's new maintainer will be Bin Liu from Texas Instruments who has accepted to take over starting with v4.6. Cc: Bin Liu Acked-by: Greg Kroah-Hartman Signed-off-by: Felipe Balbi --- MAINTAINERS | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index cc2f753cb357..65f34bb04d7a 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3444,7 +3444,6 @@ F: drivers/usb/dwc2/ DESIGNWARE USB3 DRD IP DRIVER M: Felipe Balbi L: linux-usb@vger.kernel.org -L: linux-omap@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained F: drivers/usb/dwc3/ @@ -7354,7 +7353,7 @@ F: drivers/tty/isicom.c F: include/linux/isicom.h MUSB MULTIPOINT HIGH SPEED DUAL-ROLE CONTROLLER -M: Felipe Balbi +M: Bin Liu L: linux-usb@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git S: Maintained @@ -7923,11 +7922,9 @@ F: drivers/media/platform/omap3isp/ F: drivers/staging/media/omap4iss/ OMAP USB SUPPORT -M: Felipe Balbi L: linux-usb@vger.kernel.org L: linux-omap@vger.kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git -S: Maintained +S: Orphan F: drivers/usb/*/*omap* F: arch/arm/*omap*/usb* From 3e5177c1919bdc7651b5056f35409d0b4d728841 Mon Sep 17 00:00:00 2001 From: Alexey Brodkin Date: Sat, 20 Feb 2016 16:04:26 +0300 Subject: [PATCH 416/489] arc: get rid of DEVTMPFS dependency on INITRAMFS_SOURCE Even though DEVTMPFS is required when our pre-built initramfs is used it is not the case in general. It is perfectly possible to use initramfs with device nodes already populated or there could be other usages, see discussion below for more detials: http://thread.gmane.org/gmane.comp.embedded.openwrt.devel/37819/focus=37821 This change removes mentioned dependency from arch/arc/Kconfig updating instead those defconfigs that are usually used with this kind of pre-build initramfs. And while at it all touched defconfigs were regenerated via savedefconfig and some options were removed: * USB is selected by other options implicitly * VGA_CONSOLE is disableb for ARC since 031e29b5877f31676739dc2f847d04c2c0732034 * EXT3_FS automatically selects EXT4_FS * MTDxxx and JFFS2_FS make no sense for AXS because AXS NAND controller is not upstreamed * NET_OSCI_LAN is not in upstream as well * ARCPGU_xxx options make no sense because ARC PGU is not yet in upstream and when it gets there all config options would be taken from devicetree Signed-off-by: Alexey Brodkin Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 2 -- arch/arc/configs/axs101_defconfig | 4 +--- arch/arc/configs/axs103_defconfig | 10 +--------- arch/arc/configs/axs103_smp_defconfig | 10 +--------- arch/arc/configs/nsim_700_defconfig | 5 ++--- arch/arc/configs/nsim_hs_defconfig | 3 +-- arch/arc/configs/nsim_hs_smp_defconfig | 6 ++---- arch/arc/configs/nsimosci_defconfig | 2 +- arch/arc/configs/nsimosci_hs_defconfig | 3 +-- arch/arc/configs/nsimosci_hs_smp_defconfig | 12 ++---------- arch/arc/configs/tb10x_defconfig | 18 ++++++------------ 11 files changed, 18 insertions(+), 57 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 0f8df0aa2eb8..4abc81907071 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -12,8 +12,6 @@ config ARC select BUILDTIME_EXTABLE_SORT select COMMON_CLK select CLONE_BACKWARDS - # ARC Busybox based initramfs absolutely relies on DEVTMPFS for /dev - select DEVTMPFS if !INITRAMFS_SOURCE="" select GENERIC_ATOMIC64 select GENERIC_CLOCKEVENTS select GENERIC_FIND_FIRST_BIT diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig index f1ac9818b751..5d4e2a07ad3e 100644 --- a/arch/arc/configs/axs101_defconfig +++ b/arch/arc/configs/axs101_defconfig @@ -39,6 +39,7 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -73,7 +74,6 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y @@ -91,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig index 323486d6ee83..87ee46b237ef 100644 --- a/arch/arc/configs/axs103_defconfig +++ b/arch/arc/configs/axs103_defconfig @@ -39,14 +39,10 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_AXS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -78,14 +74,12 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set # CONFIG_LOGO_LINUX_CLUT224 is not set -CONFIG_USB=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -97,12 +91,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig index 66191cd0447e..d80daf4f7e73 100644 --- a/arch/arc/configs/axs103_smp_defconfig +++ b/arch/arc/configs/axs103_smp_defconfig @@ -40,14 +40,10 @@ CONFIG_IP_PNP_RARP=y # CONFIG_INET_XFRM_MODE_TUNNEL is not set # CONFIG_INET_XFRM_MODE_BEET is not set # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_MTD=y -CONFIG_MTD_CMDLINE_PARTS=y -CONFIG_MTD_BLOCK=y -CONFIG_MTD_NAND=y -CONFIG_MTD_NAND_AXS=y CONFIG_SCSI=y CONFIG_BLK_DEV_SD=y CONFIG_NETDEVICES=y @@ -79,14 +75,12 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_DESIGNWARE_PLATFORM=y # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y CONFIG_LOGO=y # CONFIG_LOGO_LINUX_MONO is not set # CONFIG_LOGO_LINUX_VGA16 is not set # CONFIG_LOGO_LINUX_CLUT224 is not set -CONFIG_USB=y CONFIG_USB_EHCI_HCD=y CONFIG_USB_EHCI_HCD_PLATFORM=y CONFIG_USB_OHCI_HCD=y @@ -98,12 +92,10 @@ CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_DW=y # CONFIG_IOMMU_SUPPORT is not set CONFIG_EXT3_FS=y -CONFIG_EXT4_FS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_NTFS_FS=y CONFIG_TMPFS=y -CONFIG_JFFS2_FS=y CONFIG_NFS_FS=y CONFIG_NLS_CODEPAGE_437=y CONFIG_NLS_ISO8859_1=y diff --git a/arch/arc/configs/nsim_700_defconfig b/arch/arc/configs/nsim_700_defconfig index 138f9d887957..f41095340b6a 100644 --- a/arch/arc/configs/nsim_700_defconfig +++ b/arch/arc/configs/nsim_700_defconfig @@ -4,6 +4,7 @@ CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -26,7 +27,6 @@ CONFIG_ARC_PLAT_SIM=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_700" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -34,6 +34,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -51,7 +52,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -63,4 +63,3 @@ CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsim_hs_defconfig b/arch/arc/configs/nsim_hs_defconfig index f68838e8068a..cfaa33cb5921 100644 --- a/arch/arc/configs/nsim_hs_defconfig +++ b/arch/arc/configs/nsim_hs_defconfig @@ -35,6 +35,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -49,7 +50,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -61,4 +61,3 @@ CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set # CONFIG_DEBUG_PREEMPT is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsim_hs_smp_defconfig b/arch/arc/configs/nsim_hs_smp_defconfig index 96bd1c20fb0b..bb2a8dc778b5 100644 --- a/arch/arc/configs/nsim_hs_smp_defconfig +++ b/arch/arc/configs/nsim_hs_smp_defconfig @@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" # CONFIG_LOCALVERSION_AUTO is not set CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y CONFIG_IKCONFIG_PROC=y @@ -21,13 +22,11 @@ CONFIG_MODULES=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_SIM=y -CONFIG_ARC_BOARD_ML509=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y CONFIG_ARC_BUILTIN_DTB_NAME="nsim_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -35,6 +34,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -49,7 +49,6 @@ CONFIG_SERIAL_ARC=y CONFIG_SERIAL_ARC_CONSOLE=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set -# CONFIG_VGA_CONSOLE is not set # CONFIG_HID is not set # CONFIG_USB_SUPPORT is not set # CONFIG_IOMMU_SUPPORT is not set @@ -60,4 +59,3 @@ CONFIG_TMPFS=y CONFIG_NFS_FS=y # CONFIG_ENABLE_WARN_DEPRECATED is not set # CONFIG_ENABLE_MUST_CHECK is not set -CONFIG_XZ_DEC=y diff --git a/arch/arc/configs/nsimosci_defconfig b/arch/arc/configs/nsimosci_defconfig index 31e1d95764ff..646182e93753 100644 --- a/arch/arc/configs/nsimosci_defconfig +++ b/arch/arc/configs/nsimosci_defconfig @@ -33,6 +33,7 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -58,7 +59,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/nsimosci_hs_defconfig b/arch/arc/configs/nsimosci_hs_defconfig index fcae66683ca0..ceca2541950d 100644 --- a/arch/arc/configs/nsimosci_hs_defconfig +++ b/arch/arc/configs/nsimosci_hs_defconfig @@ -34,12 +34,12 @@ CONFIG_UNIX_DIAG=y CONFIG_NET_KEY=y CONFIG_INET=y # CONFIG_IPV6 is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set # CONFIG_BLK_DEV is not set CONFIG_NETDEVICES=y -CONFIG_NET_OSCI_LAN=y CONFIG_INPUT_EVDEV=y # CONFIG_MOUSE_PS2_ALPS is not set # CONFIG_MOUSE_PS2_LOGIPS2PP is not set @@ -58,7 +58,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/nsimosci_hs_smp_defconfig b/arch/arc/configs/nsimosci_hs_smp_defconfig index b01b659168ea..4b6da90f6f26 100644 --- a/arch/arc/configs/nsimosci_hs_smp_defconfig +++ b/arch/arc/configs/nsimosci_hs_smp_defconfig @@ -2,6 +2,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="ARCLinux" # CONFIG_SWAP is not set CONFIG_SYSVIPC=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NO_HZ=y CONFIG_HIGH_RES_TIMERS=y CONFIG_IKCONFIG=y @@ -18,15 +19,11 @@ CONFIG_MODULES=y # CONFIG_IOSCHED_DEADLINE is not set # CONFIG_IOSCHED_CFQ is not set CONFIG_ARC_PLAT_SIM=y -CONFIG_ARC_BOARD_ML509=y CONFIG_ISA_ARCV2=y CONFIG_SMP=y -CONFIG_ARC_HAS_LL64=y -# CONFIG_ARC_HAS_RTSC is not set CONFIG_ARC_BUILTIN_DTB_NAME="nsimosci_hs_idu" CONFIG_PREEMPT=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_PACKET_DIAG=y @@ -40,6 +37,7 @@ CONFIG_INET=y # CONFIG_INET_LRO is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y # CONFIG_STANDALONE is not set # CONFIG_PREVENT_FIRMWARE_BUILD is not set # CONFIG_FIRMWARE_IN_KERNEL is not set @@ -56,14 +54,11 @@ CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_STMICRO is not set # CONFIG_NET_VENDOR_VIA is not set # CONFIG_NET_VENDOR_WIZNET is not set -CONFIG_NET_OSCI_LAN=y # CONFIG_WLAN is not set CONFIG_INPUT_EVDEV=y CONFIG_MOUSE_PS2_TOUCHKIT=y # CONFIG_SERIO_SERPORT is not set -CONFIG_SERIO_LIBPS2=y CONFIG_SERIO_ARC_PS2=y -CONFIG_VT_HW_CONSOLE_BINDING=y # CONFIG_LEGACY_PTYS is not set # CONFIG_DEVKMEM is not set CONFIG_SERIAL_8250=y @@ -75,9 +70,6 @@ CONFIG_SERIAL_OF_PLATFORM=y # CONFIG_HW_RANDOM is not set # CONFIG_HWMON is not set CONFIG_FB=y -CONFIG_ARCPGU_RGB888=y -CONFIG_ARCPGU_DISPTYPE=0 -# CONFIG_VGA_CONSOLE is not set CONFIG_FRAMEBUFFER_CONSOLE=y CONFIG_LOGO=y # CONFIG_HID is not set diff --git a/arch/arc/configs/tb10x_defconfig b/arch/arc/configs/tb10x_defconfig index 3b4dc9cebcf1..9b342eaf95ae 100644 --- a/arch/arc/configs/tb10x_defconfig +++ b/arch/arc/configs/tb10x_defconfig @@ -3,6 +3,7 @@ CONFIG_CROSS_COMPILE="arc-linux-" CONFIG_DEFAULT_HOSTNAME="tb10x" CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y +# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_HIGH_RES_TIMERS=y CONFIG_BSD_PROCESS_ACCT=y CONFIG_BSD_PROCESS_ACCT_V3=y @@ -26,12 +27,10 @@ CONFIG_MODULE_UNLOAD=y # CONFIG_BLOCK is not set CONFIG_ARC_PLAT_TB10X=y CONFIG_ARC_CACHE_LINE_SHIFT=5 -CONFIG_ARC_STACK_NONEXEC=y CONFIG_HZ=250 CONFIG_ARC_BUILTIN_DTB_NAME="abilis_tb100_dvk" CONFIG_PREEMPT_VOLUNTARY=y # CONFIG_COMPACTION is not set -# CONFIG_CROSS_MEMORY_ATTACH is not set CONFIG_NET=y CONFIG_PACKET=y CONFIG_UNIX=y @@ -44,8 +43,8 @@ CONFIG_IP_MULTICAST=y # CONFIG_INET_DIAG is not set # CONFIG_IPV6 is not set # CONFIG_WIRELESS is not set +CONFIG_DEVTMPFS=y # CONFIG_FIRMWARE_IN_KERNEL is not set -CONFIG_PROC_DEVICETREE=y CONFIG_NETDEVICES=y # CONFIG_NET_CADENCE is not set # CONFIG_NET_VENDOR_BROADCOM is not set @@ -55,9 +54,6 @@ CONFIG_NETDEVICES=y # CONFIG_NET_VENDOR_NATSEMI is not set # CONFIG_NET_VENDOR_SEEQ is not set CONFIG_STMMAC_ETH=y -CONFIG_STMMAC_DEBUG_FS=y -CONFIG_STMMAC_DA=y -CONFIG_STMMAC_CHAINED=y # CONFIG_NET_VENDOR_WIZNET is not set # CONFIG_WLAN is not set # CONFIG_INPUT is not set @@ -91,7 +87,6 @@ CONFIG_LEDS_TRIGGER_DEFAULT_ON=y CONFIG_LEDS_TRIGGER_TRANSIENT=y CONFIG_DMADEVICES=y CONFIG_DW_DMAC=y -CONFIG_NET_DMA=y CONFIG_ASYNC_TX_DMA=y # CONFIG_IOMMU_SUPPORT is not set # CONFIG_DNOTIFY is not set @@ -100,17 +95,16 @@ CONFIG_TMPFS=y CONFIG_CONFIGFS_FS=y # CONFIG_MISC_FILESYSTEMS is not set # CONFIG_NETWORK_FILESYSTEMS is not set +CONFIG_DEBUG_INFO=y # CONFIG_ENABLE_WARN_DEPRECATED is not set -CONFIG_MAGIC_SYSRQ=y CONFIG_STRIP_ASM_SYMS=y CONFIG_DEBUG_FS=y CONFIG_HEADERS_CHECK=y CONFIG_DEBUG_SECTION_MISMATCH=y +CONFIG_MAGIC_SYSRQ=y +CONFIG_DEBUG_MEMORY_INIT=y +CONFIG_DEBUG_STACKOVERFLOW=y CONFIG_DETECT_HUNG_TASK=y CONFIG_SCHEDSTATS=y CONFIG_TIMER_STATS=y -CONFIG_DEBUG_INFO=y -CONFIG_DEBUG_MEMORY_INIT=y -CONFIG_DEBUG_STACKOVERFLOW=y -# CONFIG_CRYPTO_ANSI_CPRNG is not set # CONFIG_CRYPTO_HW is not set From b7052cd7bcf3c1478796e93e3dff2b44c9e82943 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 18 Feb 2016 18:55:54 +0000 Subject: [PATCH 417/489] sunrpc/cache: fix off-by-one in qword_get() The qword_get() function NUL-terminates its output buffer. If the input string is in hex format \xXXXX... and the same length as the output buffer, there is an off-by-one: int qword_get(char **bpp, char *dest, int bufsize) { ... while (len < bufsize) { ... *dest++ = (h << 4) | l; len++; } ... *dest = '\0'; return len; } This patch ensures the NUL terminator doesn't fall outside the output buffer. Signed-off-by: Stefan Hajnoczi Cc: stable@vger.kernel.org Signed-off-by: J. Bruce Fields --- net/sunrpc/cache.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 2b32fd602669..273bc3a35425 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -1225,7 +1225,7 @@ int qword_get(char **bpp, char *dest, int bufsize) if (bp[0] == '\\' && bp[1] == 'x') { /* HEX STRING */ bp += 2; - while (len < bufsize) { + while (len < bufsize - 1) { int h, l; h = hex_to_bin(bp[0]); From 236cf17c2502007a9d2dda3c39fb0d9a6bd03cc2 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Tue, 16 Feb 2016 14:47:31 +0000 Subject: [PATCH 418/489] KVM: arm/arm64: vgic: Ensure bitmaps are long enough When we allocate bitmaps in vgic_vcpu_init_maps, we divide the number of bits we need by 8 to figure out how many bytes to allocate. However, bitmap elements are always accessed as unsigned longs, and if we didn't happen to allocate a size such that size % sizeof(unsigned long) == 0, bitmap accesses may go past the end of the allocation. When using KASAN (which does byte-granular access checks), this results in a continuous stream of BUGs whenever these bitmaps are accessed: ============================================================================= BUG kmalloc-128 (Tainted: G B ): kasan: bad access detected ----------------------------------------------------------------------------- INFO: Allocated in vgic_init.part.25+0x55c/0x990 age=7493 cpu=3 pid=1730 INFO: Slab 0xffffffbde6d5da40 objects=16 used=15 fp=0xffffffc935769700 flags=0x4000000000000080 INFO: Object 0xffffffc935769500 @offset=1280 fp=0x (null) Bytes b4 ffffffc9357694f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769500: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769510: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769520: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769530: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769540: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769550: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769560: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Object ffffffc935769570: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695b0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695d0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695e0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ Padding ffffffc9357695f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ CPU: 3 PID: 1740 Comm: kvm-vcpu-0 Tainted: G B 4.4.0+ #17 Hardware name: ARM Juno development board (r1) (DT) Call trace: [] dump_backtrace+0x0/0x280 [] show_stack+0x14/0x20 [] dump_stack+0x100/0x188 [] print_trailer+0xfc/0x168 [] object_err+0x3c/0x50 [] kasan_report_error+0x244/0x558 [] __asan_report_load8_noabort+0x48/0x50 [] __bitmap_or+0xc0/0xc8 [] kvm_vgic_flush_hwstate+0x1bc/0x650 [] kvm_arch_vcpu_ioctl_run+0x2ec/0xa60 [] kvm_vcpu_ioctl+0x474/0xa68 [] do_vfs_ioctl+0x5b8/0xcb0 [] SyS_ioctl+0x8c/0xa0 [] el0_svc_naked+0x24/0x28 Memory state around the buggy address: ffffffc935769400: 00 00 fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffffc935769480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffffffc935769500: 04 fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ^ ffffffc935769580: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffffffc935769600: 00 00 00 00 fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Fix the issue by always allocating a multiple of sizeof(unsigned long), as we do elsewhere in the vgic code. Fixes: c1bfb577a ("arm/arm64: KVM: vgic: switch to dynamic allocation") Cc: stable@vger.kernel.org Acked-by: Marc Zyngier Acked-by: Christoffer Dall Signed-off-by: Mark Rutland Signed-off-by: Marc Zyngier --- virt/kvm/arm/vgic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 043032c6a5a4..00429b392c61 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -1875,8 +1875,8 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; - - int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8; + int nr_longs = BITS_TO_LONGS(nr_irqs - VGIC_NR_PRIVATE_IRQS); + int sz = nr_longs * sizeof(unsigned long); vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL); vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL); From de9e478b9d49f3a0214310d921450cf5bb4a21e6 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 23 Feb 2016 14:58:52 -0800 Subject: [PATCH 419/489] x86: fix SMAP in 32-bit environments In commit 11f1a4b9755f ("x86: reorganize SMAP handling in user space accesses") I changed how the stac/clac instructions were generated around the user space accesses, which then made it possible to do batched accesses efficiently for user string copies etc. However, in doing so, I completely spaced out, and didn't even think about the 32-bit case. And nobody really even seemed to notice, because SMAP doesn't even exist until modern Skylake processors, and you'd have to be crazy to run 32-bit kernels on a modern CPU. Which brings us to Andy Lutomirski. He actually tested the 32-bit kernel on new hardware, and noticed that it doesn't work. My bad. The trivial fix is to add the required uaccess begin/end markers around the raw accesses in . I feel a bit bad about this patch, just because that header file really should be cleaned up to avoid all the duplicated code in it, and this commit just expands on the problem. But this just fixes the bug without any bigger cleanup surgery. Reported-and-tested-by: Andy Lutomirski Signed-off-by: Linus Torvalds --- arch/x86/include/asm/uaccess_32.h | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h index f5dcb5204dcd..3fe0eac59462 100644 --- a/arch/x86/include/asm/uaccess_32.h +++ b/arch/x86/include/asm/uaccess_32.h @@ -48,20 +48,28 @@ __copy_to_user_inatomic(void __user *to, const void *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret, 4); + __uaccess_end(); return ret; case 8: + __uaccess_begin(); __put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret, 8); + __uaccess_end(); return ret; } } @@ -103,13 +111,19 @@ __copy_from_user_inatomic(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -148,13 +162,19 @@ __copy_from_user(void *to, const void __user *from, unsigned long n) switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } @@ -170,13 +190,19 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to, switch (n) { case 1: + __uaccess_begin(); __get_user_size(*(u8 *)to, from, 1, ret, 1); + __uaccess_end(); return ret; case 2: + __uaccess_begin(); __get_user_size(*(u16 *)to, from, 2, ret, 2); + __uaccess_end(); return ret; case 4: + __uaccess_begin(); __get_user_size(*(u32 *)to, from, 4, ret, 4); + __uaccess_end(); return ret; } } From 4577b0665515e0abc7bc72562d6328d179598815 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 17 Feb 2016 13:08:58 -0800 Subject: [PATCH 420/489] nfit: update address range scrub commands to the acpi 6.1 format The original format of these commands from the "NVDIMM DSM Interface Example" [1] are superseded by the ACPI 6.1 definition of the "NVDIMM Root Device _DSMs" [2]. [1]: http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf [2]: http://www.uefi.org/sites/default/files/resources/ACPI_6_1.pdf "9.20.7 NVDIMM Root Device _DSMs" Changes include: 1/ New 'restart' fields in ars_status, unfortunately these are implemented in the middle of the existing definition so this change is not backwards compatible. The expectation is that shipping platforms will only ever support the ACPI 6.1 definition. 2/ New status values for ars_start ('busy') and ars_status ('overflow'). Cc: Vishal Verma Cc: Linda Knippers Cc: Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 6 +++--- drivers/nvdimm/bus.c | 12 ++++++------ include/linux/libnvdimm.h | 2 +- include/uapi/linux/ndctl.h | 11 +++++++++-- 4 files changed, 19 insertions(+), 12 deletions(-) diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index 1d4b9c6bdf45..fb53db187854 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -1503,9 +1503,7 @@ static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, case 1: /* ARS unsupported, but we should never get here */ return 0; - case 2: - return -EINVAL; - case 3: + case 6: /* ARS is in progress */ msleep(1000); break; @@ -1537,6 +1535,8 @@ static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, case 2: /* No ARS performed for the current boot */ return 0; + case 3: + /* TODO: error list overflow support */ default: return -ENXIO; } diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 99953b34fa1d..5d28e9405f32 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -382,14 +382,14 @@ static const struct nd_cmd_desc __nd_cmd_bus_descs[] = { [ND_CMD_ARS_CAP] = { .in_num = 2, .in_sizes = { 8, 8, }, - .out_num = 2, - .out_sizes = { 4, 4, }, + .out_num = 4, + .out_sizes = { 4, 4, 4, 4, }, }, [ND_CMD_ARS_START] = { - .in_num = 4, - .in_sizes = { 8, 8, 2, 6, }, - .out_num = 1, - .out_sizes = { 4, }, + .in_num = 5, + .in_sizes = { 8, 8, 2, 1, 5, }, + .out_num = 2, + .out_sizes = { 4, 4, }, }, [ND_CMD_ARS_STATUS] = { .out_num = 3, diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index c736382fd260..141ffdd59960 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -26,7 +26,7 @@ enum { /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, - ND_CMD_MAX_ELEM = 4, + ND_CMD_MAX_ELEM = 5, ND_CMD_MAX_ENVELOPE = 16, ND_MAX_MAPPINGS = 32, diff --git a/include/uapi/linux/ndctl.h b/include/uapi/linux/ndctl.h index 5b4a4be06e2b..cc68b92124d4 100644 --- a/include/uapi/linux/ndctl.h +++ b/include/uapi/linux/ndctl.h @@ -66,14 +66,18 @@ struct nd_cmd_ars_cap { __u64 length; __u32 status; __u32 max_ars_out; + __u32 clear_err_unit; + __u32 reserved; } __packed; struct nd_cmd_ars_start { __u64 address; __u64 length; __u16 type; - __u8 reserved[6]; + __u8 flags; + __u8 reserved[5]; __u32 status; + __u32 scrub_time; } __packed; struct nd_cmd_ars_status { @@ -81,11 +85,14 @@ struct nd_cmd_ars_status { __u32 out_length; __u64 address; __u64 length; + __u64 restart_address; + __u64 restart_length; __u16 type; + __u16 flags; __u32 num_records; struct nd_ars_record { __u32 handle; - __u32 flags; + __u32 reserved; __u64 err_address; __u64 length; } __packed records[0]; From 93f834df9c2d4e362dfdc4b05daa0a4e18814836 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Sat, 20 Feb 2016 14:32:24 -0800 Subject: [PATCH 421/489] devm_memremap: Fix error value when memremap failed devm_memremap() returns an ERR_PTR() value in case of error. However, it returns NULL when memremap() failed. This causes the caller, such as the pmem driver, to proceed and oops later. Change devm_memremap() to return ERR_PTR(-ENXIO) when memremap() failed. Signed-off-by: Toshi Kani Cc: Andrew Morton Cc: Reviewed-by: Ross Zwisler Signed-off-by: Dan Williams --- kernel/memremap.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/memremap.c b/kernel/memremap.c index 2c468dea60bc..b04ea2f5fbfe 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -136,8 +136,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset, if (addr) { *ptr = addr; devres_add(dev, ptr); - } else + } else { devres_free(ptr); + return ERR_PTR(-ENXIO); + } return addr; } From c45442055dfdeb265cc20c9eeaa9fd11a75fbf51 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 22 Feb 2016 22:58:34 +0100 Subject: [PATCH 422/489] nvdimm: use 'u64' for pfn flags A recent bugfix changed pfn_t to always be 64-bit wide, but did not change the code in pmem.c, which is now broken on 32-bit architectures as reported by gcc: In file included from ../drivers/nvdimm/pmem.c:28:0: drivers/nvdimm/pmem.c: In function 'pmem_alloc': include/linux/pfn_t.h:15:17: error: large integer implicitly truncated to unsigned type [-Werror=overflow] #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3)) This changes the intermediate pfn_flags in struct pmem_device to be 64 bit wide as well, so they can store the flags correctly. Signed-off-by: Arnd Bergmann Fixes: db78c22230d0 ("mm: fix pfn_t vs highmem") Signed-off-by: Dan Williams --- drivers/nvdimm/pmem.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 7edf31671dab..8d0b54670184 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -41,7 +41,7 @@ struct pmem_device { phys_addr_t phys_addr; /* when non-zero this device is hosting a 'pfn' instance */ phys_addr_t data_offset; - unsigned long pfn_flags; + u64 pfn_flags; void __pmem *virt_addr; size_t size; struct badblocks bb; From bb143f814ea488769ca2e79e0b376139cb5f134b Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 23 Feb 2016 11:55:16 +0530 Subject: [PATCH 423/489] ARCv2: SMP: Emulate IPI to self using software triggered interrupt ARConnect/MCIP Inter-Core-Interrupt module can't send interrupt to local core. So use core intc capability to trigger software interrupt to self, using an unsued IRQ #21. This showed up as csd deadlock with LTP trace_sched on a dual core system. This test acts as scheduler fuzzer, triggering all sorts of schedulting activity. Trouble starts with IPI to self, which doesn't get delivered (effectively lost due to H/w capability), but the msg intended to be sent remain enqueued in per-cpu @ipi_data. All subsequent IPIs to this core from other cores get elided due to the IPI coalescing optimization in ipi_send_msg_one() where a pending msg implies an IPI already sent and assumes other core is yet to ack it. After the elided IPI, other core simply goes into csd_lock_wait() but never comes out as this core never sees the interrupt. Fixes STAR 9001008624 Cc: Peter Zijlstra Cc: [4.2] Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irqflags-arcv2.h | 11 +++++++++++ arch/arc/kernel/entry-arcv2.S | 11 ++++++----- arch/arc/kernel/mcip.c | 15 +++++++++++++++ 3 files changed, 32 insertions(+), 5 deletions(-) diff --git a/arch/arc/include/asm/irqflags-arcv2.h b/arch/arc/include/asm/irqflags-arcv2.h index 1fc18ee06cf2..37c2f751eebf 100644 --- a/arch/arc/include/asm/irqflags-arcv2.h +++ b/arch/arc/include/asm/irqflags-arcv2.h @@ -22,6 +22,7 @@ #define AUX_IRQ_CTRL 0x00E #define AUX_IRQ_ACT 0x043 /* Active Intr across all levels */ #define AUX_IRQ_LVL_PEND 0x200 /* Pending Intr across all levels */ +#define AUX_IRQ_HINT 0x201 /* For generating Soft Interrupts */ #define AUX_IRQ_PRIORITY 0x206 #define ICAUSE 0x40a #define AUX_IRQ_SELECT 0x40b @@ -115,6 +116,16 @@ static inline int arch_irqs_disabled(void) return arch_irqs_disabled_flags(arch_local_save_flags()); } +static inline void arc_softirq_trigger(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, irq); +} + +static inline void arc_softirq_clear(int irq) +{ + write_aux_reg(AUX_IRQ_HINT, 0); +} + #else .macro IRQ_DISABLE scratch diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S index b17830294706..c1264607bbff 100644 --- a/arch/arc/kernel/entry-arcv2.S +++ b/arch/arc/kernel/entry-arcv2.S @@ -45,11 +45,12 @@ VECTOR reserved ; Reserved slots VECTOR handle_interrupt ; (16) Timer0 VECTOR handle_interrupt ; unused (Timer1) VECTOR handle_interrupt ; unused (WDT) -VECTOR handle_interrupt ; (19) ICI (inter core interrupt) -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt -VECTOR handle_interrupt ; (23) End of fixed IRQs +VECTOR handle_interrupt ; (19) Inter core Interrupt (IPI) +VECTOR handle_interrupt ; (20) perf Interrupt +VECTOR handle_interrupt ; (21) Software Triggered Intr (Self IPI) +VECTOR handle_interrupt ; unused +VECTOR handle_interrupt ; (23) unused +# End of fixed IRQs .rept CONFIG_ARC_NUMBER_OF_INTERRUPTS - 8 VECTOR handle_interrupt diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 002c5fcf8947..9e1bd03b87a6 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -11,9 +11,12 @@ #include #include #include +#include #include #include +#define SOFTIRQ_IRQ 21 + static char smp_cpuinfo_buf[128]; static int idu_detected; @@ -22,6 +25,7 @@ static DEFINE_RAW_SPINLOCK(mcip_lock); static void mcip_setup_per_cpu(int cpu) { smp_ipi_irq_setup(cpu, IPI_IRQ); + smp_ipi_irq_setup(cpu, SOFTIRQ_IRQ); } static void mcip_ipi_send(int cpu) @@ -29,6 +33,12 @@ static void mcip_ipi_send(int cpu) unsigned long flags; int ipi_was_pending; + /* ARConnect can only send IPI to others */ + if (unlikely(cpu == raw_smp_processor_id())) { + arc_softirq_trigger(SOFTIRQ_IRQ); + return; + } + /* * NOTE: We must spin here if the other cpu hasn't yet * serviced a previous message. This can burn lots @@ -63,6 +73,11 @@ static void mcip_ipi_clear(int irq) unsigned long flags; unsigned int __maybe_unused copy; + if (unlikely(irq == SOFTIRQ_IRQ)) { + arc_softirq_clear(irq); + return; + } + raw_spin_lock_irqsave(&mcip_lock, flags); /* Who sent the IPI */ From dbcbc7e7cee15058fdb9696b2b38c692680fc413 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Thu, 28 Jan 2016 12:48:05 +0530 Subject: [PATCH 424/489] ARC: [intc-compact] Remove IPI setup from ARCompact port There is no real ARC700 based SMP SoC so remove IPI definition. EZChip's SMP ARC700 is going to use a different intc and IPI provider anyways. Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irq.h | 1 - arch/arc/kernel/intc-compact.c | 3 --- 2 files changed, 4 deletions(-) diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index 4fd7d62a6e30..bc5103637326 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -16,7 +16,6 @@ #ifdef CONFIG_ISA_ARCOMPACT #define TIMER0_IRQ 3 #define TIMER1_IRQ 4 -#define IPI_IRQ (NR_CPU_IRQS-1) /* dummy to enable SMP build for up hardware */ #else #define TIMER0_IRQ 16 #define TIMER1_IRQ 17 diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c index 06bcedf19b62..224d1c3aa9c4 100644 --- a/arch/arc/kernel/intc-compact.c +++ b/arch/arc/kernel/intc-compact.c @@ -81,9 +81,6 @@ static int arc_intc_domain_map(struct irq_domain *d, unsigned int irq, { switch (irq) { case TIMER0_IRQ: -#ifdef CONFIG_SMP - case IPI_IRQ: -#endif irq_set_chip_and_handler(irq, &onchip_intc, handle_percpu_irq); break; default: From 9681787930cec7cee77db0a93c747153ef962b8a Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Tue, 23 Feb 2016 13:35:12 +0530 Subject: [PATCH 425/489] ARCv2: SMP: Push IPI_IRQ into IPI provider Signed-off-by: Vineet Gupta --- arch/arc/include/asm/irq.h | 1 - arch/arc/kernel/mcip.c | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arc/include/asm/irq.h b/arch/arc/include/asm/irq.h index bc5103637326..49014f0ef36d 100644 --- a/arch/arc/include/asm/irq.h +++ b/arch/arc/include/asm/irq.h @@ -19,7 +19,6 @@ #else #define TIMER0_IRQ 16 #define TIMER1_IRQ 17 -#define IPI_IRQ 19 #endif #include diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 9e1bd03b87a6..e30d5d428330 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -15,6 +15,7 @@ #include #include +#define IPI_IRQ 19 #define SOFTIRQ_IRQ 21 static char smp_cpuinfo_buf[128]; From 3dea30ca5bef0e013abe857057a952a9d6757fe5 Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 19 Feb 2016 07:57:41 +0530 Subject: [PATCH 426/489] ARCv2: Elide sending new cross core intr if receiver didn't ack prev ARConnect/MCIP IPI sending has a retry-wait loop in case caller had not seen a previous such interrupt. Turns out that it is not needed at all. Linux cross core calling allows coalescing multiple IPIs to same receiver - it is fine as long as there is one. This logic is built into upper layer already, at a higher level of abstraction. ipi_send_msg_one() sets the actual msg payload, but it only calls MCIP IPI sending if msg holder was empty (using atomic-set-new-and-get-old construct). Thus it is unlikely that the retry-wait looping was ever getting exercised at all. Cc: Chuck Jordan Cc: Peter Zijlstra Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 27 ++++++++++----------------- 1 file changed, 10 insertions(+), 17 deletions(-) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index e30d5d428330..7afc3c703ed1 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -40,26 +40,19 @@ static void mcip_ipi_send(int cpu) return; } + raw_spin_lock_irqsave(&mcip_lock, flags); + /* - * NOTE: We must spin here if the other cpu hasn't yet - * serviced a previous message. This can burn lots - * of time, but we MUST follows this protocol or - * ipi messages can be lost!!! - * Also, we must release the lock in this loop because - * the other side may get to this same loop and not - * be able to ack -- thus causing deadlock. + * If receiver already has a pending interrupt, elide sending this one. + * Linux cross core calling works well with concurrent IPIs + * coalesced into one + * see arch/arc/kernel/smp.c: ipi_send_msg_one() */ + __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); + ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); + if (!ipi_was_pending) + __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); - do { - raw_spin_lock_irqsave(&mcip_lock, flags); - __mcip_cmd(CMD_INTRPT_READ_STATUS, cpu); - ipi_was_pending = read_aux_reg(ARC_REG_MCIP_READBACK); - if (ipi_was_pending == 0) - break; /* break out but keep lock */ - raw_spin_unlock_irqrestore(&mcip_lock, flags); - } while (1); - - __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); #ifdef CONFIG_ARC_IPI_DBG From d73b73f5626ac0b131b31b7b9457e19201bc570b Mon Sep 17 00:00:00 2001 From: Vineet Gupta Date: Fri, 19 Feb 2016 08:18:11 +0530 Subject: [PATCH 427/489] ARC: SMP: No need for CONFIG_ARC_IPI_DBG This was more relevant during SMP bringup. The warning for bogus msg better be visible always. Signed-off-by: Vineet Gupta --- arch/arc/Kconfig | 8 -------- arch/arc/kernel/mcip.c | 9 +-------- arch/arc/kernel/smp.c | 3 --- 3 files changed, 1 insertion(+), 19 deletions(-) diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 4abc81907071..8a188bc1786a 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -532,14 +532,6 @@ config ARC_DBG_TLB_MISS_COUNT Counts number of I and D TLB Misses and exports them via Debugfs The counters can be cleared via Debugfs as well -if SMP - -config ARC_IPI_DBG - bool "Debug Inter Core interrupts" - default n - -endif - endif config ARC_UBOOT_SUPPORT diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 7afc3c703ed1..7b4af70ffd18 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -65,7 +65,6 @@ static void mcip_ipi_clear(int irq) { unsigned int cpu, c; unsigned long flags; - unsigned int __maybe_unused copy; if (unlikely(irq == SOFTIRQ_IRQ)) { arc_softirq_clear(irq); @@ -77,7 +76,7 @@ static void mcip_ipi_clear(int irq) /* Who sent the IPI */ __mcip_cmd(CMD_INTRPT_CHECK_SOURCE, 0); - copy = cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ + cpu = read_aux_reg(ARC_REG_MCIP_READBACK); /* 1,2,4,8... */ /* * In rare case, multiple concurrent IPIs sent to same target can @@ -91,12 +90,6 @@ static void mcip_ipi_clear(int irq) } while (cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); - -#ifdef CONFIG_ARC_IPI_DBG - if (c != __ffs(copy)) - pr_info("IPIs from %x coalesced to %x\n", - copy, raw_smp_processor_id()); -#endif } static void mcip_probe_n_setup(void) diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c index ef6e9e15b82a..424e937da5c8 100644 --- a/arch/arc/kernel/smp.c +++ b/arch/arc/kernel/smp.c @@ -336,11 +336,8 @@ irqreturn_t do_IPI(int irq, void *dev_id) int rc; rc = __do_IPI(msg); -#ifdef CONFIG_ARC_IPI_DBG - /* IPI received but no valid @msg */ if (rc) pr_info("IPI with bogus msg %ld in %ld\n", msg, copy); -#endif pending &= ~(1U << msg); } while (pending); From 04d1d281dcfe683a53cddfab8371fc8bb302b069 Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Tue, 23 Feb 2016 13:19:29 -0800 Subject: [PATCH 428/489] x86/entry/32: Add an ASM_CLAC to entry_SYSENTER_32 Both before and after 5f310f739b4c ("x86/entry/32: Re-implement SYSENTER using the new C path"), we relied on a uaccess very early in the SYSENTER path to clear AC. After that change, though, we can potentially make it all the way into C code with AC set, which enlarges the attack surface for SMAP bypass by doing SYSENTER with AC set. Strengthen the SMAP protection by addding the missing ASM_CLAC right at the beginning. Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Brian Gerst Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/3e36be110724896e32a4a1fe73bacb349d3cba94.1456262295.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_32.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 77d8c5112900..bb3e376d0f33 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -294,6 +294,7 @@ sysenter_past_esp: pushl $__USER_DS /* pt_regs->ss */ pushl %ebp /* pt_regs->sp (stashed in bp) */ pushfl /* pt_regs->flags (except IF = 0) */ + ASM_CLAC /* Clear AC after saving FLAGS */ orl $X86_EFLAGS_IF, (%esp) /* Fix IF */ pushl $__USER_CS /* pt_regs->cs */ pushl $0 /* pt_regs->ip = 0 (placeholder) */ From 5e45a2589d24573c564630990c88ac93659f8fe4 Mon Sep 17 00:00:00 2001 From: Ludovic Desroches Date: Fri, 19 Feb 2016 20:21:17 +0100 Subject: [PATCH 429/489] ARM: at91/dt: fix typo in sama5d2 pinmux descriptions PIN_PA15 macro has the same value as PIN_PA14 so we were overriding PA14 mux/configuration. Signed-off-by: Ludovic Desroches Reported-by: Cyrille Pitchen Fixes: 7f16cb676c00 ("ARM: at91/dt: add sama5d2 pinmux") Cc: # v4.4+ Signed-off-by: Alexandre Belloni Signed-off-by: Olof Johansson --- arch/arm/boot/dts/sama5d2-pinfunc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm/boot/dts/sama5d2-pinfunc.h b/arch/arm/boot/dts/sama5d2-pinfunc.h index 1afe24629d1f..b0c912feaa2f 100644 --- a/arch/arm/boot/dts/sama5d2-pinfunc.h +++ b/arch/arm/boot/dts/sama5d2-pinfunc.h @@ -90,7 +90,7 @@ #define PIN_PA14__I2SC1_MCK PINMUX_PIN(PIN_PA14, 4, 2) #define PIN_PA14__FLEXCOM3_IO2 PINMUX_PIN(PIN_PA14, 5, 1) #define PIN_PA14__D9 PINMUX_PIN(PIN_PA14, 6, 2) -#define PIN_PA15 14 +#define PIN_PA15 15 #define PIN_PA15__GPIO PINMUX_PIN(PIN_PA15, 0, 0) #define PIN_PA15__SPI0_MOSI PINMUX_PIN(PIN_PA15, 1, 1) #define PIN_PA15__TF1 PINMUX_PIN(PIN_PA15, 2, 1) From a9e5547b1908ee282b875470a08c96acf17656d6 Mon Sep 17 00:00:00 2001 From: Antoine Tenart Date: Mon, 22 Feb 2016 14:22:30 +0100 Subject: [PATCH 430/489] MAINTAINERS: alpine: add a new maintainer and update the entry Add myself as a co-maintainer for the Alpine support. Also update the entry to take in account Alpine ARM64 boards, Alpine ARM device trees and Alpine-specific drivers. Signed-off-by: Antoine Tenart Acked-by: Tsahee Zidenberg Signed-off-by: Olof Johansson --- MAINTAINERS | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 4978dc19a4d2..42cc0d76296d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -929,8 +929,12 @@ N: meson[x68] ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg +M: Antoine Tenart S: Maintained F: arch/arm/mach-alpine/ +F: arch/arm/boot/dts/alpine* +F: arch/arm64/boot/dts/al/ +F: drivers/*/*alpine* ARM/ATMEL AT91RM9200, AT91SAM9 AND SAMA5 SOC SUPPORT M: Nicolas Ferre From 79318452cb36678bde20d384dc3eab537d930d3e Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Tue, 23 Feb 2016 10:43:11 +0100 Subject: [PATCH 431/489] MAINTAINERS: Extend info, add wiki and ml for meson arch Update the maintainers info with wiki and mailing list for the meson platform. Fix a wrong file attribution and add maintainership for the generic meson platforms. Signed-off-by: Carlo Caione Signed-off-by: Olof Johansson --- MAINTAINERS | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 42cc0d76296d..536adfcf1319 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -920,12 +920,15 @@ M: Emilio López S: Maintained F: drivers/clk/sunxi/ -ARM/Amlogic MesonX SoC support +ARM/Amlogic Meson SoC support M: Carlo Caione L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +L: linux-meson@googlegroups.com +W: http://linux-meson.com/ S: Maintained -F: drivers/media/rc/meson-ir.c -N: meson[x68] +F: arch/arm/mach-meson/ +F: arch/arm/boot/dts/meson* +N: meson ARM/Annapurna Labs ALPINE ARCHITECTURE M: Tsahee Zidenberg From 9ef2d8be55652804205a34dcbfec78b933c0ea30 Mon Sep 17 00:00:00 2001 From: Valentin Rothberg Date: Wed, 24 Feb 2016 09:40:22 +0100 Subject: [PATCH 432/489] arc: SMP: CONFIG_ARC_IPI_DBG cleanup Previous Commit ("ARC: SMP: No need for CONFIG_ARC_IPI_DBG") removed the Kconfig option ARC_IPI_DBG. Remove the last reference on this option. Signed-off-by: Valentin Rothberg Signed-off-by: Vineet Gupta --- arch/arc/kernel/mcip.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c index 7b4af70ffd18..c41c364b926c 100644 --- a/arch/arc/kernel/mcip.c +++ b/arch/arc/kernel/mcip.c @@ -54,11 +54,6 @@ static void mcip_ipi_send(int cpu) __mcip_cmd(CMD_INTRPT_GENERATE_IRQ, cpu); raw_spin_unlock_irqrestore(&mcip_lock, flags); - -#ifdef CONFIG_ARC_IPI_DBG - if (ipi_was_pending) - pr_info("IPI ACK delayed from cpu %d\n", cpu); -#endif } static void mcip_ipi_clear(int irq) From 1d6a821277aaa0cdd666278aaff93298df313d41 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 15 Feb 2016 17:04:04 +0000 Subject: [PATCH 433/489] arm/arm64: KVM: Feed initialized memory to MMIO accesses On an MMIO access, we always copy the on-stack buffer info the shared "run" structure, even if this is a read access. This ends up leaking up to 8 bytes of uninitialized memory into userspace, depending on the size of the access. An obvious fix for this one is to only perform the copy if this is an actual write. Reviewed-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 7f33b2056ae6..0f6600f05137 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -206,7 +206,8 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, run->mmio.is_write = is_write; run->mmio.phys_addr = fault_ipa; run->mmio.len = len; - memcpy(run->mmio.data, data_buf, len); + if (is_write) + memcpy(run->mmio.data, data_buf, len); if (!ret) { /* We handled the access successfully in the kernel. */ From 5ec5d10682745d3280a37e8ffee1ddcd37ecfa94 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 24 Feb 2016 13:53:46 +0100 Subject: [PATCH 434/489] Revert "ACPI / PCI: Simplify acpi_penalize_isa_irq()" Revert commit 0971686954f9 "ACPI / PCI: Simplify acpi_penalize_isa_irq()" that depends on commit b5bd02695471 (ACPI, PCI, irq: remove interrupt count restriction) which introduced a regression and needs to be reverted for this reason. Signed-off-by: Rafael J. Wysocki --- drivers/acpi/pci_link.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index fa2863567eed..5114d8007aa0 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -877,9 +877,17 @@ static int __init acpi_irq_penalty_update(char *str, int used) */ void acpi_penalize_isa_irq(int irq, int active) { - if (irq >= 0) - acpi_irq_add_penalty(irq, active ? - PIRQ_PENALTY_ISA_USED : PIRQ_PENALTY_PCI_USING); + int penalty; + + if (irq < 0) + return; + + if (active) + penalty = PIRQ_PENALTY_ISA_USED; + else + penalty = PIRQ_PENALTY_PCI_USING; + + acpi_irq_add_penalty(irq, penalty); } bool acpi_isa_irq_available(int irq) From e249714571db26cdb1ae8df7ed39971bafa041a7 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 24 Feb 2016 13:55:38 +0100 Subject: [PATCH 435/489] Revert "ACPI, PCI, irq: remove interrupt count restriction" Revert commit b5bd02695471 (ACPI, PCI, irq: remove interrupt count restriction) that introduced a boot regression on some systems where it caused kmalloc() to be used too early. Link: http://marc.info/?l=linux-acpi&m=145580159209240&w=2 Reported-by: Nalla, Ravikanth Signed-off-by: Rafael J. Wysocki --- drivers/acpi/pci_link.c | 136 ++++++++++------------------------------ 1 file changed, 34 insertions(+), 102 deletions(-) diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 5114d8007aa0..ededa909df2f 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -4,7 +4,6 @@ * Copyright (C) 2001, 2002 Andy Grover * Copyright (C) 2001, 2002 Paul Diefenbaugh * Copyright (C) 2002 Dominik Brodowski - * Copyright (c) 2015, The Linux Foundation. All rights reserved. * * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ * @@ -438,6 +437,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) * enabled system. */ +#define ACPI_MAX_IRQS 256 #define ACPI_MAX_ISA_IRQ 16 #define PIRQ_PENALTY_PCI_AVAILABLE (0) @@ -447,7 +447,7 @@ static int acpi_pci_link_set(struct acpi_pci_link *link, int irq) #define PIRQ_PENALTY_ISA_USED (16*16*16*16*16) #define PIRQ_PENALTY_ISA_ALWAYS (16*16*16*16*16*16) -static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = { +static int acpi_irq_penalty[ACPI_MAX_IRQS] = { PIRQ_PENALTY_ISA_ALWAYS, /* IRQ0 timer */ PIRQ_PENALTY_ISA_ALWAYS, /* IRQ1 keyboard */ PIRQ_PENALTY_ISA_ALWAYS, /* IRQ2 cascade */ @@ -464,68 +464,9 @@ static int acpi_irq_isa_penalty[ACPI_MAX_ISA_IRQ] = { PIRQ_PENALTY_ISA_USED, /* IRQ13 fpe, sometimes */ PIRQ_PENALTY_ISA_USED, /* IRQ14 ide0 */ PIRQ_PENALTY_ISA_USED, /* IRQ15 ide1 */ + /* >IRQ15 */ }; -struct irq_penalty_info { - int irq; - int penalty; - struct list_head node; -}; - -static LIST_HEAD(acpi_irq_penalty_list); - -static int acpi_irq_get_penalty(int irq) -{ - struct irq_penalty_info *irq_info; - - if (irq < ACPI_MAX_ISA_IRQ) - return acpi_irq_isa_penalty[irq]; - - list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) { - if (irq_info->irq == irq) - return irq_info->penalty; - } - - return 0; -} - -static int acpi_irq_set_penalty(int irq, int new_penalty) -{ - struct irq_penalty_info *irq_info; - - /* see if this is a ISA IRQ */ - if (irq < ACPI_MAX_ISA_IRQ) { - acpi_irq_isa_penalty[irq] = new_penalty; - return 0; - } - - /* next, try to locate from the dynamic list */ - list_for_each_entry(irq_info, &acpi_irq_penalty_list, node) { - if (irq_info->irq == irq) { - irq_info->penalty = new_penalty; - return 0; - } - } - - /* nope, let's allocate a slot for this IRQ */ - irq_info = kzalloc(sizeof(*irq_info), GFP_KERNEL); - if (!irq_info) - return -ENOMEM; - - irq_info->irq = irq; - irq_info->penalty = new_penalty; - list_add_tail(&irq_info->node, &acpi_irq_penalty_list); - - return 0; -} - -static void acpi_irq_add_penalty(int irq, int penalty) -{ - int curpen = acpi_irq_get_penalty(irq); - - acpi_irq_set_penalty(irq, curpen + penalty); -} - int __init acpi_irq_penalty_init(void) { struct acpi_pci_link *link; @@ -546,16 +487,15 @@ int __init acpi_irq_penalty_init(void) link->irq.possible_count; for (i = 0; i < link->irq.possible_count; i++) { - if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) { - int irqpos = link->irq.possible[i]; - - acpi_irq_add_penalty(irqpos, penalty); - } + if (link->irq.possible[i] < ACPI_MAX_ISA_IRQ) + acpi_irq_penalty[link->irq. + possible[i]] += + penalty; } } else if (link->irq.active) { - acpi_irq_add_penalty(link->irq.active, - PIRQ_PENALTY_PCI_POSSIBLE); + acpi_irq_penalty[link->irq.active] += + PIRQ_PENALTY_PCI_POSSIBLE; } } @@ -607,12 +547,12 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) * the use of IRQs 9, 10, 11, and >15. */ for (i = (link->irq.possible_count - 1); i >= 0; i--) { - if (acpi_irq_get_penalty(irq) > - acpi_irq_get_penalty(link->irq.possible[i])) + if (acpi_irq_penalty[irq] > + acpi_irq_penalty[link->irq.possible[i]]) irq = link->irq.possible[i]; } } - if (acpi_irq_get_penalty(irq) >= PIRQ_PENALTY_ISA_ALWAYS) { + if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) { printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. " "Try pci=noacpi or acpi=off\n", acpi_device_name(link->device), @@ -628,8 +568,7 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) acpi_device_bid(link->device)); return -ENODEV; } else { - acpi_irq_add_penalty(link->irq.active, PIRQ_PENALTY_PCI_USING); - + acpi_irq_penalty[link->irq.active] += PIRQ_PENALTY_PCI_USING; printk(KERN_WARNING PREFIX "%s [%s] enabled at IRQ %d\n", acpi_device_name(link->device), acpi_device_bid(link->device), link->irq.active); @@ -839,7 +778,7 @@ static void acpi_pci_link_remove(struct acpi_device *device) } /* - * modify penalty from cmdline + * modify acpi_irq_penalty[] from cmdline */ static int __init acpi_irq_penalty_update(char *str, int used) { @@ -857,10 +796,13 @@ static int __init acpi_irq_penalty_update(char *str, int used) if (irq < 0) continue; + if (irq >= ARRAY_SIZE(acpi_irq_penalty)) + continue; + if (used) - acpi_irq_add_penalty(irq, PIRQ_PENALTY_ISA_USED); + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED; else - acpi_irq_set_penalty(irq, PIRQ_PENALTY_PCI_AVAILABLE); + acpi_irq_penalty[irq] = PIRQ_PENALTY_PCI_AVAILABLE; if (retval != 2) /* no next number */ break; @@ -877,23 +819,18 @@ static int __init acpi_irq_penalty_update(char *str, int used) */ void acpi_penalize_isa_irq(int irq, int active) { - int penalty; - - if (irq < 0) - return; - - if (active) - penalty = PIRQ_PENALTY_ISA_USED; - else - penalty = PIRQ_PENALTY_PCI_USING; - - acpi_irq_add_penalty(irq, penalty); + if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) { + if (active) + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_USED; + else + acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING; + } } bool acpi_isa_irq_available(int irq) { - return irq >= 0 && - (acpi_irq_get_penalty(irq) < PIRQ_PENALTY_ISA_ALWAYS); + return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) || + acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS); } /* @@ -903,18 +840,13 @@ bool acpi_isa_irq_available(int irq) */ void acpi_penalize_sci_irq(int irq, int trigger, int polarity) { - int penalty; - - if (irq < 0) - return; - - if (trigger != ACPI_MADT_TRIGGER_LEVEL || - polarity != ACPI_MADT_POLARITY_ACTIVE_LOW) - penalty = PIRQ_PENALTY_ISA_ALWAYS; - else - penalty = PIRQ_PENALTY_PCI_USING; - - acpi_irq_add_penalty(irq, penalty); + if (irq >= 0 && irq < ARRAY_SIZE(acpi_irq_penalty)) { + if (trigger != ACPI_MADT_TRIGGER_LEVEL || + polarity != ACPI_MADT_POLARITY_ACTIVE_LOW) + acpi_irq_penalty[irq] += PIRQ_PENALTY_ISA_ALWAYS; + else + acpi_irq_penalty[irq] += PIRQ_PENALTY_PCI_USING; + } } /* From 172b2386ed16a9143d9a456aae5ec87275c61489 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Wed, 10 Feb 2016 17:50:23 +0100 Subject: [PATCH 436/489] KVM: x86: fix missed hardware breakpoints Sometimes when setting a breakpoint a process doesn't stop on it. This is because the debug registers are not loaded correctly on VCPU load. The following simple reproducer from Oleg Nesterov tries using debug registers in two threads. To see the bug, run a 2-VCPU guest with "taskset -c 0" and run "./bp 0 1" inside the guest. #include #include #include #include #include #include #include #include #include #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER) unsigned long encode_dr7(int drnum, int enable, unsigned int type, unsigned int len) { unsigned long dr7; dr7 = ((len | type) & 0xf) << (DR_CONTROL_SHIFT + drnum * DR_CONTROL_SIZE); if (enable) dr7 |= (DR_GLOBAL_ENABLE << (drnum * DR_ENABLE_SIZE)); return dr7; } int write_dr(int pid, int dr, unsigned long val) { return ptrace(PTRACE_POKEUSER, pid, offsetof (struct user, u_debugreg[dr]), val); } void set_bp(pid_t pid, void *addr) { unsigned long dr7; assert(write_dr(pid, 0, (long)addr) == 0); dr7 = encode_dr7(0, 1, DR_RW_EXECUTE, DR_LEN_1); assert(write_dr(pid, 7, dr7) == 0); } void *get_rip(int pid) { return (void*)ptrace(PTRACE_PEEKUSER, pid, offsetof(struct user, regs.rip), 0); } void test(int nr) { void *bp_addr = &&label + nr, *bp_hit; int pid; printf("test bp %d\n", nr); assert(nr < 16); // see 16 asm nops below pid = fork(); if (!pid) { assert(ptrace(PTRACE_TRACEME, 0,0,0) == 0); kill(getpid(), SIGSTOP); for (;;) { label: asm ( "nop; nop; nop; nop;" "nop; nop; nop; nop;" "nop; nop; nop; nop;" "nop; nop; nop; nop;" ); } } assert(pid == wait(NULL)); set_bp(pid, bp_addr); for (;;) { assert(ptrace(PTRACE_CONT, pid, 0, 0) == 0); assert(pid == wait(NULL)); bp_hit = get_rip(pid); if (bp_hit != bp_addr) fprintf(stderr, "ERR!! hit wrong bp %ld != %d\n", bp_hit - &&label, nr); } } int main(int argc, const char *argv[]) { while (--argc) { int nr = atoi(*++argv); if (!fork()) test(nr); } while (wait(NULL) > 0) ; return 0; } Cc: stable@vger.kernel.org Suggested-by: Nadav Amit Reported-by: Andrey Wagin Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4244c2baf57d..f4891f2ece23 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2752,6 +2752,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) } kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD; } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) From 0c1d77f4ba5cc9c05a29adca3d6466cdf4969b70 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Fri, 19 Feb 2016 18:07:21 +0100 Subject: [PATCH 437/489] KVM: x86: fix conversion of addresses to linear in 32-bit protected mode Commit e8dd2d2d641c ("Silence compiler warning in arch/x86/kvm/emulate.c", 2015-09-06) broke boot of the Hurd. The bug is that the "default:" case actually could modify "la", but after the patch this change is not reflected in *linear. The bug is visible whenever a non-zero segment base causes the linear address to wrap around the 4GB mark. Fixes: e8dd2d2d641cb2724ee10e76c0ad02e04289c017 Cc: stable@vger.kernel.org Reported-by: Aurelien Jarno Tested-by: Aurelien Jarno Signed-off-by: Paolo Bonzini --- arch/x86/kvm/emulate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 1505587d06e9..b9b09fec173b 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -650,10 +650,10 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, u16 sel; la = seg_base(ctxt, addr.seg) + addr.ea; - *linear = la; *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: + *linear = la; if (is_noncanonical_address(la)) goto bad; @@ -662,6 +662,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, goto bad; break; default: + *linear = la = (u32)la; usable = ctxt->ops->get_segment(ctxt, &sel, &desc, NULL, addr.seg); if (!usable) @@ -689,7 +690,6 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (size > *max_size) goto bad; } - la &= (u32)-1; break; } if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) From d7444794a02ff655eda87e3cc54e86b940e7736f Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Fri, 19 Feb 2016 13:11:46 +0100 Subject: [PATCH 438/489] KVM: async_pf: do not warn on page allocation failures In async_pf we try to allocate with NOWAIT to get an element quickly or fail. This code also handle failures gracefully. Lets silence potential page allocation failures under load. qemu-system-s39: page allocation failure: order:0,mode:0x2200000 [...] Call Trace: ([<00000000001146b8>] show_trace+0xf8/0x148) [<000000000011476a>] show_stack+0x62/0xe8 [<00000000004a36b8>] dump_stack+0x70/0x98 [<0000000000272c3a>] warn_alloc_failed+0xd2/0x148 [<000000000027709e>] __alloc_pages_nodemask+0x94e/0xb38 [<00000000002cd36a>] new_slab+0x382/0x400 [<00000000002cf7ac>] ___slab_alloc.constprop.30+0x2dc/0x378 [<00000000002d03d0>] kmem_cache_alloc+0x160/0x1d0 [<0000000000133db4>] kvm_setup_async_pf+0x6c/0x198 [<000000000013dee8>] kvm_arch_vcpu_ioctl_run+0xd48/0xd58 [<000000000012fcaa>] kvm_vcpu_ioctl+0x372/0x690 [<00000000002f66f6>] do_vfs_ioctl+0x3be/0x510 [<00000000002f68ec>] SyS_ioctl+0xa4/0xb8 [<0000000000781c5e>] system_call+0xd6/0x264 [<000003ffa24fa06a>] 0x3ffa24fa06a Cc: stable@vger.kernel.org Signed-off-by: Christian Borntraeger Reviewed-by: Dominik Dingel Signed-off-by: Paolo Bonzini --- virt/kvm/async_pf.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 353159922456..db2dd3335c6a 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -172,7 +172,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva, * do alloc nowait since if we are going to sleep anyway we * may as well sleep faulting in page */ - work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT); + work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN); if (!work) return 0; From d045437a169f899dfb0f6f7ede24cc042543ced9 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Wed, 24 Feb 2016 09:04:24 -0500 Subject: [PATCH 439/489] tracing: Fix showing function event in available_events The ftrace:function event is only displayed for parsing the function tracer data. It is not used to enable function tracing, and does not include an "enable" file in its event directory. Originally, this event was kept separate from other events because it did not have a ->reg parameter. But perf added a "reg" parameter for its use which caused issues, because it made the event available to functions where it was not compatible for. Commit 9b63776fa3ca9 "tracing: Do not enable function event with enable" added a TRACE_EVENT_FL_IGNORE_ENABLE flag that prevented the function event from being enabled by normal trace events. But this commit missed keeping the function event from being displayed by the "available_events" directory, which is used to show what events can be enabled by set_event. One documented way to enable all events is to: cat available_events > set_event But because the function event is displayed in the available_events, this now causes an INVALID error: cat: write error: Invalid argument Reported-by: Chunyu Hu Fixes: 9b63776fa3ca9 "tracing: Do not enable function event with enable" Cc: stable@vger.kernel.org # 3.4+ Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f333e57c4614..ab09829d3b97 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -869,7 +869,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && call->class->reg) + if (call->class && call->class->reg && + !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) return file; } From fd451b90e78c4178bcfc5072f2b2b637500c109a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 17 Feb 2016 10:25:05 +0000 Subject: [PATCH 440/489] arm64: KVM: vgic-v3: Restore ICH_APR0Rn_EL2 before ICH_APR1Rn_EL2 The GICv3 architecture spec says: Writing to the active priority registers in any order other than the following order will result in UNPREDICTABLE behavior: - ICH_AP0R_EL2. - ICH_AP1R_EL2. So let's not pointlessly go against the rule... Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/vgic-v3-sr.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index 9142e082f5f3..5dd2a26444ec 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -147,16 +147,6 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) max_lr_idx = vtr_to_max_lr_idx(val); nr_pri_bits = vtr_to_nr_pri_bits(val); - switch (nr_pri_bits) { - case 7: - write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); - write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); - case 6: - write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); - default: - write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); - } - switch (nr_pri_bits) { case 7: write_gicreg(cpu_if->vgic_ap0r[3], ICH_AP0R3_EL2); @@ -167,6 +157,16 @@ void __hyp_text __vgic_v3_restore_state(struct kvm_vcpu *vcpu) write_gicreg(cpu_if->vgic_ap0r[0], ICH_AP0R0_EL2); } + switch (nr_pri_bits) { + case 7: + write_gicreg(cpu_if->vgic_ap1r[3], ICH_AP1R3_EL2); + write_gicreg(cpu_if->vgic_ap1r[2], ICH_AP1R2_EL2); + case 6: + write_gicreg(cpu_if->vgic_ap1r[1], ICH_AP1R1_EL2); + default: + write_gicreg(cpu_if->vgic_ap1r[0], ICH_AP1R0_EL2); + } + switch (max_lr_idx) { case 15: write_gicreg(cpu_if->vgic_lr[VGIC_V3_LR_INDEX(15)], ICH_LR15_EL2); From 827108d08070c7515c14eb47e5fa03f59cfe38cf Mon Sep 17 00:00:00 2001 From: Bradley Pankow Date: Mon, 22 Feb 2016 20:11:47 -0500 Subject: [PATCH 441/489] amdgpu: fix NULL pointer dereference at tonga_check_states_equal The event_data passed from pem_fini was not cleared upon initialization. This caused NULL checks to pass and cast_const_phw_tonga_power_state to attempt to dereference an invalid pointer. Clear the event_data in pem_init and pem_fini before calling pem_handle_event. Reviewed-by: Rex Zhu Signed-off-by: Bradley Pankow Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c index 52a3efc97f05..46410e3c7349 100644 --- a/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c +++ b/drivers/gpu/drm/amd/powerplay/eventmgr/eventmgr.c @@ -31,7 +31,7 @@ static int pem_init(struct pp_eventmgr *eventmgr) { int result = 0; - struct pem_event_data event_data; + struct pem_event_data event_data = { {0} }; /* Initialize PowerPlay feature info */ pem_init_feature_info(eventmgr); @@ -52,7 +52,7 @@ static int pem_init(struct pp_eventmgr *eventmgr) static void pem_fini(struct pp_eventmgr *eventmgr) { - struct pem_event_data event_data; + struct pem_event_data event_data = { {0} }; pem_uninit_featureInfo(eventmgr); pem_unregister_interrupts(eventmgr); From 6378076bcfdcd1d4f8d726d08d3fa044736873eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Christian=20K=C3=B6nig?= Date: Fri, 19 Feb 2016 10:03:03 +0100 Subject: [PATCH 442/489] drm/amdgpu: disable direct VM updates when vm_debug is set MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit That should make user space bugs more obvious. Signed-off-by: Christian König Reviewed-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c index 7380f782cd14..d20c2a8929cb 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c @@ -596,7 +596,8 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data, break; } ttm_eu_backoff_reservation(&ticket, &list); - if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE)) + if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && + !amdgpu_vm_debug) amdgpu_gem_va_update_vm(adev, bo_va, args->operation); drm_gem_object_unreference_unlocked(gobj); From 2ac015e293bbe3858533009612eac58842daf325 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Wed, 24 Feb 2016 18:58:03 +0300 Subject: [PATCH 443/489] thp: call pmdp_invalidate() with correct virtual address Sebastian Ott and Gerald Schaefer reported random crashes on s390. It was bisected to my THP refcounting patchset. The problem is that pmdp_invalidated() called with wrong virtual address. It got offset up by HPAGE_PMD_SIZE by loop over ptes. The solution is to introduce new variable to be used in loop and don't touch 'haddr'. Signed-off-by: Kirill A. Shutemov Reported-and-tested-by: Gerald Schaefer Reported-and-tested-by Sebastian Ott Reviewed-by: Will Deacon Cc: Christian Borntraeger Cc: Martin Schwidefsky Cc: Aneesh Kumar K.V Cc: Andrea Arcangeli Cc: Sasha Levin Cc: Jerome Marchand Cc: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1c317b85ea7d..e10a4fee88d2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2836,6 +2836,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable_t pgtable; pmd_t _pmd; bool young, write, dirty; + unsigned long addr; int i; VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); @@ -2865,7 +2866,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry, *pte; /* * Note that NUMA hinting access restrictions are not @@ -2886,9 +2887,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, } if (dirty) SetPageDirty(page + i); - pte = pte_offset_map(&_pmd, haddr); + pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); - set_pte_at(mm, haddr, pte, entry); + set_pte_at(mm, addr, pte, entry); atomic_inc(&page[i]._mapcount); pte_unmap(pte); } @@ -2938,7 +2939,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pmd_populate(mm, pmd, pgtable); if (freeze) { - for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) { + for (i = 0; i < HPAGE_PMD_NR; i++) { page_remove_rmap(page + i, false); put_page(page + i); } From e7a88e82fe380459b864e05b372638aeacb0f52d Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Wed, 17 Feb 2016 20:04:08 +0100 Subject: [PATCH 444/489] libceph: don't bail early from try_read() when skipping a message The contract between try_read() and try_write() is that when called each processes as much data as possible. When instructed by osd_client to skip a message, try_read() is violating this contract by returning after receiving and discarding a single message instead of checking for more. try_write() then gets a chance to write out more requests, generating more replies/skips for try_read() to handle, forcing the messenger into a starvation loop. Cc: stable@vger.kernel.org # 3.10+ Reported-by: Varada Kari Signed-off-by: Ilya Dryomov Tested-by: Varada Kari Reviewed-by: Alex Elder --- net/ceph/messenger.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 9cfedf565f5b..fec20819a5ea 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -2337,7 +2337,7 @@ static int read_partial_message(struct ceph_connection *con) con->in_base_pos = -front_len - middle_len - data_len - sizeof(m->footer); con->in_tag = CEPH_MSGR_TAG_READY; - return 0; + return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { pr_err("read_partial_message bad seq %lld expected %lld\n", seq, con->in_seq + 1); @@ -2363,7 +2363,7 @@ static int read_partial_message(struct ceph_connection *con) sizeof(m->footer); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; - return 0; + return 1; } BUG_ON(!con->in_msg); From dbc0d3caff5b7591e0cf8e34ca686ca6f4479ee1 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 19 Feb 2016 11:38:57 +0100 Subject: [PATCH 445/489] libceph: use the right footer size when skipping a message ceph_msg_footer is 21 bytes long, while ceph_msg_footer_old is only 13. Don't skip too much when CEPH_FEATURE_MSG_AUTH isn't negotiated. Cc: stable@vger.kernel.org # 3.19+ Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder --- net/ceph/messenger.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index fec20819a5ea..9382619a405b 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1197,6 +1197,13 @@ static bool ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, return new_piece; } +static size_t sizeof_footer(struct ceph_connection *con) +{ + return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ? + sizeof(struct ceph_msg_footer) : + sizeof(struct ceph_msg_footer_old); +} + static void prepare_message_data(struct ceph_msg *msg, u32 data_len) { BUG_ON(!msg); @@ -2335,7 +2342,7 @@ static int read_partial_message(struct ceph_connection *con) ceph_pr_addr(&con->peer_addr.in_addr), seq, con->in_seq + 1); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; return 1; } else if ((s64)seq - (s64)con->in_seq > 1) { @@ -2360,7 +2367,7 @@ static int read_partial_message(struct ceph_connection *con) /* skip this message */ dout("alloc_msg said skip message\n"); con->in_base_pos = -front_len - middle_len - data_len - - sizeof(m->footer); + sizeof_footer(con); con->in_tag = CEPH_MSGR_TAG_READY; con->in_seq++; return 1; From cd8140c673d9ba9be3591220e1b2226d9e1e40d3 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 19 Feb 2016 11:38:57 +0100 Subject: [PATCH 446/489] libceph: don't spam dmesg with stray reply warnings Commit d15f9d694b77 ("libceph: check data_len in ->alloc_msg()") mistakenly bumped the log level on the "tid %llu unknown, skipping" message. Turn it back into a dout() - stray replies are perfectly normal when OSDs flap, crash, get killed for testing purposes, etc. Cc: stable@vger.kernel.org # 4.3+ Signed-off-by: Ilya Dryomov Reviewed-by: Alex Elder --- net/ceph/osd_client.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 3534e12683d3..5bc053778fed 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -2853,8 +2853,8 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, mutex_lock(&osdc->request_mutex); req = __lookup_request(osdc, tid); if (!req) { - pr_warn("%s osd%d tid %llu unknown, skipping\n", - __func__, osd->o_osd, tid); + dout("%s osd%d tid %llu unknown, skipping\n", __func__, + osd->o_osd, tid); m = NULL; *skip = 1; goto out; From 0378ba4899d5fbd8494ed6580cbc81d7b44dbac6 Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Wed, 24 Feb 2016 09:43:23 +0100 Subject: [PATCH 447/489] drivers: sh: Restore legacy clock domain on SuperH platforms CONFIG_ARCH_SHMOBILE is not only enabled for Renesas ARM platforms (which are DT based and multi-platform), but also on a select set of Renesas SuperH platforms (SH7722/SH7723/SH7724/SH7343/SH7366). Hence since commit 0ba58de231066e47 ("drivers: sh: Get rid of CONFIG_ARCH_SHMOBILE_MULTI"), the legacy clock domain is no longer installed on these SuperH platforms, and module clocks may not be enabled when needed, leading to driver failures. To fix this, add an additional check for CONFIG_OF. Fixes: 0ba58de231066e47 ("drivers: sh: Get rid of CONFIG_ARCH_SHMOBILE_MULTI"). Signed-off-by: Geert Uytterhoeven Signed-off-by: Simon Horman --- drivers/sh/pm_runtime.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c index 91a003011acf..a9bac3bf20de 100644 --- a/drivers/sh/pm_runtime.c +++ b/drivers/sh/pm_runtime.c @@ -34,7 +34,7 @@ static struct pm_clk_notifier_block platform_bus_notifier = { static int __init sh_pm_runtime_init(void) { - if (IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_ARCH_SHMOBILE)) { if (!of_find_compatible_node(NULL, NULL, "renesas,cpg-mstp-clocks")) return 0; From 870571a5698b2e9d0f4d2e5c6245967b582aab45 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Wed, 24 Feb 2016 18:34:43 +0100 Subject: [PATCH 448/489] drm/nouveau: platform: Fix deferred probe The error cleanup paths aren't quite correct and will crash upon deferred probe. Cc: stable@vger.kernel.org # v4.3+ Reviewed-by: Ben Skeggs Reviewed-by: Alexandre Courbot Signed-off-by: Thierry Reding Signed-off-by: Dave Airlie --- drivers/gpu/drm/nouveau/nouveau_platform.c | 2 +- .../drm/nouveau/nvkm/engine/device/tegra.c | 40 ++++++++++++++----- 2 files changed, 30 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c index 8a70cec59bcd..2dfe58af12e4 100644 --- a/drivers/gpu/drm/nouveau/nouveau_platform.c +++ b/drivers/gpu/drm/nouveau/nouveau_platform.c @@ -24,7 +24,7 @@ static int nouveau_platform_probe(struct platform_device *pdev) { const struct nvkm_device_tegra_func *func; - struct nvkm_device *device; + struct nvkm_device *device = NULL; struct drm_device *drm; int ret; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c index 7f8a42721eb2..e7e581d6a8ff 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c @@ -252,32 +252,40 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, if (!(tdev = kzalloc(sizeof(*tdev), GFP_KERNEL))) return -ENOMEM; - *pdevice = &tdev->device; + tdev->func = func; tdev->pdev = pdev; tdev->irq = -1; tdev->vdd = devm_regulator_get(&pdev->dev, "vdd"); - if (IS_ERR(tdev->vdd)) - return PTR_ERR(tdev->vdd); + if (IS_ERR(tdev->vdd)) { + ret = PTR_ERR(tdev->vdd); + goto free; + } tdev->rst = devm_reset_control_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->rst)) - return PTR_ERR(tdev->rst); + if (IS_ERR(tdev->rst)) { + ret = PTR_ERR(tdev->rst); + goto free; + } tdev->clk = devm_clk_get(&pdev->dev, "gpu"); - if (IS_ERR(tdev->clk)) - return PTR_ERR(tdev->clk); + if (IS_ERR(tdev->clk)) { + ret = PTR_ERR(tdev->clk); + goto free; + } tdev->clk_pwr = devm_clk_get(&pdev->dev, "pwr"); - if (IS_ERR(tdev->clk_pwr)) - return PTR_ERR(tdev->clk_pwr); + if (IS_ERR(tdev->clk_pwr)) { + ret = PTR_ERR(tdev->clk_pwr); + goto free; + } nvkm_device_tegra_probe_iommu(tdev); ret = nvkm_device_tegra_power_up(tdev); if (ret) - return ret; + goto remove; tdev->gpu_speedo = tegra_sku_info.gpu_speedo_value; ret = nvkm_device_ctor(&nvkm_device_tegra_func, NULL, &pdev->dev, @@ -285,9 +293,19 @@ nvkm_device_tegra_new(const struct nvkm_device_tegra_func *func, cfg, dbg, detect, mmio, subdev_mask, &tdev->device); if (ret) - return ret; + goto powerdown; + + *pdevice = &tdev->device; return 0; + +powerdown: + nvkm_device_tegra_power_down(tdev); +remove: + nvkm_device_tegra_remove_iommu(tdev); +free: + kfree(tdev); + return ret; } #else int From 95664e66fad964c3dd7945d6edfb1d0931844664 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Thu, 18 Feb 2016 08:14:19 +1000 Subject: [PATCH 449/489] drm/nouveau/disp/dp: ensure sink is powered up before attempting link training This can happen under some annoying circumstances, and is a quick fix until more substantial changes can be made. Fixed eDP mode changes on (at least) the Lenovo P50. Signed-off-by: Ben Skeggs Cc: stable@vger.kernel.org --- drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c | 10 ++++++++++ drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h | 6 ++++++ 2 files changed, 16 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c index 74e2f7c6c07e..9688970eca47 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.c @@ -328,6 +328,7 @@ nvkm_dp_train(struct work_struct *w) .outp = outp, }, *dp = &_dp; u32 datarate = 0; + u8 pwr; int ret; if (!outp->base.info.location && disp->func->sor.magic) @@ -355,6 +356,15 @@ nvkm_dp_train(struct work_struct *w) /* disable link interrupt handling during link training */ nvkm_notify_put(&outp->irq); + /* ensure sink is not in a low-power state */ + if (!nvkm_rdaux(outp->aux, DPCD_SC00, &pwr, 1)) { + if ((pwr & DPCD_SC00_SET_POWER) != DPCD_SC00_SET_POWER_D0) { + pwr &= ~DPCD_SC00_SET_POWER; + pwr |= DPCD_SC00_SET_POWER_D0; + nvkm_wraux(outp->aux, DPCD_SC00, &pwr, 1); + } + } + /* enable down-spreading and execute pre-train script from vbios */ dp_link_train_init(dp, outp->dpcd[3] & 0x01); diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h index 9596290329c7..6e10c5e0ef11 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/dport.h @@ -71,5 +71,11 @@ #define DPCD_LS0C_LANE1_POST_CURSOR2 0x0c #define DPCD_LS0C_LANE0_POST_CURSOR2 0x03 +/* DPCD Sink Control */ +#define DPCD_SC00 0x00600 +#define DPCD_SC00_SET_POWER 0x03 +#define DPCD_SC00_SET_POWER_D0 0x01 +#define DPCD_SC00_SET_POWER_D3 0x03 + void nvkm_dp_train(struct work_struct *); #endif From 3d44d51bd339766f0178f0cf2e8d048b4a4872aa Mon Sep 17 00:00:00 2001 From: Andy Lutomirski Date: Wed, 24 Feb 2016 12:18:49 -0800 Subject: [PATCH 450/489] x86/entry/compat: Add missing CLAC to entry_INT80_32 This doesn't seem to fix a regression -- I don't think the CLAC was ever there. I double-checked in a debugger: entries through the int80 gate do not automatically clear AC. Stable maintainers: I can provide a backport to 4.3 and earlier if needed. This needs to be backported all the way to 3.10. Reported-by: Brian Gerst Signed-off-by: Andy Lutomirski Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Denys Vlasenko Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: # v3.10 and later Fixes: 63bcff2a307b ("x86, smap: Add STAC and CLAC instructions to control user space access") Link: http://lkml.kernel.org/r/b02b7e71ae54074be01fc171cbd4b72517055c0e.1456345086.git.luto@kernel.org Signed-off-by: Ingo Molnar --- arch/x86/entry/entry_64_compat.S | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index ff1c6d61f332..3c990eeee40b 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -261,6 +261,7 @@ ENTRY(entry_INT80_compat) * Interrupts are off on entry. */ PARAVIRT_ADJUST_EXCEPTION_FRAME + ASM_CLAC /* Do this early to minimize exposure */ SWAPGS /* From 84c4e620d35f49f486a900af214ad12276afb386 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:40 +0100 Subject: [PATCH 451/489] perf: Close install vs. exit race Consider the following scenario: CPU0 CPU1 ctx = find_get_ctx(); perf_event_exit_task_context() mutex_lock(&ctx->mutex); perf_install_in_context(ctx, ...); /* NO-OP */ mutex_unlock(&ctx->mutex); ... perf_release() WARN_ON_ONCE(event->state != STATE_EXIT); Since the event doesn't pass through perf_remove_from_context() because perf_install_in_context() NO-OPs because the ctx is dead, and perf_event_exit_task_context() will not observe the event because its not attached yet, the event->state will not be set. Solve this by revalidating ctx->task after we acquire ctx->mutex and failing the event creation as a whole. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.626853419@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 35 ++++++++++++++++++++++++++--------- 1 file changed, 26 insertions(+), 9 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 0d58522103cd..d7b0316e3465 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2158,13 +2158,15 @@ perf_install_in_context(struct perf_event_context *ctx, */ raw_spin_lock_irq(&ctx->lock); task = ctx->task; + /* - * Worse, we cannot even rely on the ctx actually existing anymore. If - * between find_get_context() and perf_install_in_context() the task - * went through perf_event_exit_task() its dead and we should not be - * adding new events. + * If between ctx = find_get_context() and mutex_lock(&ctx->mutex) the + * ctx gets destroyed, we must not install an event into it. + * + * This is normally tested for after we acquire the mutex, so this is + * a sanity check. */ - if (task == TASK_TOMBSTONE) { + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { raw_spin_unlock_irq(&ctx->lock); return; } @@ -8389,10 +8391,19 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { gctx = group_leader->ctx; mutex_lock_double(&gctx->mutex, &ctx->mutex); + if (gctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } } else { mutex_lock(&ctx->mutex); } + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } + if (!perf_event_validate_size(event)) { err = -E2BIG; goto err_locked; @@ -8563,12 +8574,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_unlock; + } + if (!exclusive_event_installable(event, ctx)) { - mutex_unlock(&ctx->mutex); - perf_unpin_context(ctx); - put_ctx(ctx); err = -EBUSY; - goto err_free; + goto err_unlock; } perf_install_in_context(ctx, event, cpu); @@ -8577,6 +8590,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, return event; +err_unlock: + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); err_free: free_event(event); err: From 130056275ade730e7a79c110212c8815202773ee Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:41 +0100 Subject: [PATCH 452/489] perf: Do not double free In case of: err_file: fput(event_file), we'll end up calling perf_release() which in turn will free the event. Do not then free the event _again_. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.697350349@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d7b0316e3465..211a5ce64e3f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -8520,7 +8520,12 @@ err_context: perf_unpin_context(ctx); put_ctx(ctx); err_alloc: - free_event(event); + /* + * If event_file is set, the fput() above will have called ->release() + * and that will take care of freeing the event. + */ + if (!event_file) + free_event(event); err_cpus: put_online_cpus(); err_task: From a4f4bb6d0c69d0bb573f1d9e6f1b806f9b038b19 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:42 +0100 Subject: [PATCH 453/489] perf: Allow perf_release() with !event->ctx In the err_file: fput(event_file) case, the event will not yet have been attached to a context. However perf_release() does assume it has been. Cure this. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.793996260@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 16 +++++++++++++--- 1 file changed, 13 insertions(+), 3 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 211a5ce64e3f..d5299e2e435d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3754,9 +3754,19 @@ static void put_event(struct perf_event *event) */ int perf_event_release_kernel(struct perf_event *event) { - struct perf_event_context *ctx; + struct perf_event_context *ctx = event->ctx; struct perf_event *child, *tmp; + /* + * If we got here through err_file: fput(event_file); we will not have + * attached to a context yet. + */ + if (!ctx) { + WARN_ON_ONCE(event->attach_state & + (PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP)); + goto no_ctx; + } + if (!is_kernel_event(event)) perf_remove_from_owner(event); @@ -3832,8 +3842,8 @@ again: } mutex_unlock(&event->child_mutex); - /* Must be the last reference */ - put_event(event); +no_ctx: + put_event(event); /* Must be the 'last' reference */ return 0; } EXPORT_SYMBOL_GPL(perf_event_release_kernel); From 6f932e5be1503ab0783699e843db325d44c2fabb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:43 +0100 Subject: [PATCH 454/489] perf: Only update context time when active Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.860690919@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d5299e2e435d..64698fbfad9f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2170,12 +2170,12 @@ perf_install_in_context(struct perf_event_context *ctx, raw_spin_unlock_irq(&ctx->lock); return; } - update_context_time(ctx); - /* - * Update cgrp time only if current cgrp matches event->cgrp. - * Must be done before calling add_event_to_ctx(). - */ - update_cgrp_time_from_event(event); + + if (ctx->is_active) { + update_context_time(ctx); + update_cgrp_time_from_event(event); + } + add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); From a69b0ca4ac3bf5427b571f11cbf33f0a32b728d5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:44 +0100 Subject: [PATCH 455/489] perf: Fix cloning Alexander reported that when the 'original' context gets destroyed, no new clones happen. This can happen irrespective of the ctx switch optimization, any task can die, even the parent, and we want to continue monitoring the task hierarchy until we either close the event or no tasks are left in the hierarchy. perf_event_init_context() will attempt to pin the 'parent' context during clone(). At that point current is the parent, and since current cannot have exited while executing clone(), its context cannot have passed through perf_event_exit_task_context(). Therefore perf_pin_task_context() cannot observe ctx->task == TASK_TOMBSTONE. However, since inherit_event() does: if (parent_event->parent) parent_event = parent_event->parent; it looks at the 'original' event when it does: is_orphaned_event(). This can return true if the context that contains the this event has passed through perf_event_exit_task_context(). And thus we'll fail to clone the perf context. Fix this by adding a new state: STATE_DEAD, which is set by perf_release() to indicate that the filedesc (or kernel reference) is dead and there are no observers for our data left. Only for STATE_DEAD will is_orphaned_event() be true and inhibit cloning. STATE_EXIT is otherwise preserved such that is_event_hup() remains functional and will report when the observed task hierarchy becomes empty. Reported-by: Alexander Shishkin Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Fixes: c6e5b73242d2 ("perf: Synchronously clean up child events") Link: http://lkml.kernel.org/r/20160224174947.919845295@infradead.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 1 + kernel/events/core.c | 29 ++++++++++++++--------------- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index b35a61a481fa..39156619e108 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -397,6 +397,7 @@ struct pmu { * enum perf_event_active_state - the states of a event */ enum perf_event_active_state { + PERF_EVENT_STATE_DEAD = -4, PERF_EVENT_STATE_EXIT = -3, PERF_EVENT_STATE_ERROR = -2, PERF_EVENT_STATE_OFF = -1, diff --git a/kernel/events/core.c b/kernel/events/core.c index 64698fbfad9f..92d6999a4f2f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1645,7 +1645,7 @@ out: static bool is_orphaned_event(struct perf_event *event) { - return event->state == PERF_EVENT_STATE_EXIT; + return event->state == PERF_EVENT_STATE_DEAD; } static inline int pmu_filter_match(struct perf_event *event) @@ -1732,7 +1732,6 @@ group_sched_out(struct perf_event *group_event, } #define DETACH_GROUP 0x01UL -#define DETACH_STATE 0x02UL /* * Cross CPU call to remove a performance event @@ -1752,8 +1751,6 @@ __perf_remove_from_context(struct perf_event *event, if (flags & DETACH_GROUP) perf_group_detach(event); list_del_event(event, ctx); - if (flags & DETACH_STATE) - event->state = PERF_EVENT_STATE_EXIT; if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; @@ -3772,22 +3769,24 @@ int perf_event_release_kernel(struct perf_event *event) ctx = perf_event_ctx_lock(event); WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, DETACH_GROUP | DETACH_STATE); - perf_event_ctx_unlock(event, ctx); + perf_remove_from_context(event, DETACH_GROUP); + raw_spin_lock_irq(&ctx->lock); /* - * At this point we must have event->state == PERF_EVENT_STATE_EXIT, - * either from the above perf_remove_from_context() or through - * perf_event_exit_event(). + * Mark this even as STATE_DEAD, there is no external reference to it + * anymore. * - * Therefore, anybody acquiring event->child_mutex after the below - * loop _must_ also see this, most importantly inherit_event() which - * will avoid placing more children on the list. + * Anybody acquiring event->child_mutex after the below loop _must_ + * also see this, most importantly inherit_event() which will avoid + * placing more children on the list. * * Thus this guarantees that we will in fact observe and kill _ALL_ * child events. */ - WARN_ON_ONCE(event->state != PERF_EVENT_STATE_EXIT); + event->state = PERF_EVENT_STATE_DEAD; + raw_spin_unlock_irq(&ctx->lock); + + perf_event_ctx_unlock(event, ctx); again: mutex_lock(&event->child_mutex); @@ -4000,7 +3999,7 @@ static bool is_event_hup(struct perf_event *event) { bool no_children; - if (event->state != PERF_EVENT_STATE_EXIT) + if (event->state > PERF_EVENT_STATE_EXIT) return false; mutex_lock(&event->child_mutex); @@ -8727,7 +8726,7 @@ perf_event_exit_event(struct perf_event *child_event, if (parent_event) perf_group_detach(child_event); list_del_event(child_event, child_ctx); - child_event->state = PERF_EVENT_STATE_EXIT; /* see perf_event_release_kernel() */ + child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */ raw_spin_unlock_irq(&child_ctx->lock); /* From 9107c89e269d2738019861bb518e3d59bef01781 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:45 +0100 Subject: [PATCH 456/489] perf: Fix race between event install and jump_labels perf_install_in_context() relies upon the context switch hooks to have scheduled in events when the IPI misses its target -- after all, if the task has moved from the CPU (or wasn't running at all), it will have to context switch to run elsewhere. This however doesn't appear to be happening. It is possible for the IPI to not happen (task wasn't running) only to later observe the task running with an inactive context. The only possible explanation is that the context switch hooks are not called. Therefore put in a sync_sched() after toggling the jump_label to guarantee all CPUs will have them enabled before we install an event. A simple if (0->1) sync_sched() will not in fact work, because any further increment can race and complete before the sync_sched(). Therefore we must jump through some hoops. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174947.980211985@infradead.org Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 6 ++--- kernel/events/core.c | 49 +++++++++++++++++++++++++++++++------- 2 files changed, 44 insertions(+), 11 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 39156619e108..f5c5a3fa2c81 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -906,7 +906,7 @@ perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) } } -extern struct static_key_deferred perf_sched_events; +extern struct static_key_false perf_sched_events; static __always_inline bool perf_sw_migrate_enabled(void) @@ -925,7 +925,7 @@ static inline void perf_event_task_migrate(struct task_struct *task) static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { - if (static_key_false(&perf_sched_events.key)) + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (perf_sw_migrate_enabled() && task->sched_migrated) { @@ -942,7 +942,7 @@ static inline void perf_event_task_sched_out(struct task_struct *prev, { perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); - if (static_key_false(&perf_sched_events.key)) + if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } diff --git a/kernel/events/core.c b/kernel/events/core.c index 92d6999a4f2f..ea064ca8dd3c 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -321,7 +321,13 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -struct static_key_deferred perf_sched_events __read_mostly; + +static void perf_sched_delayed(struct work_struct *work); +DEFINE_STATIC_KEY_FALSE(perf_sched_events); +static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed); +static DEFINE_MUTEX(perf_sched_mutex); +static atomic_t perf_sched_count; + static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static DEFINE_PER_CPU(int, perf_sched_cb_usages); @@ -3536,12 +3542,22 @@ static void unaccount_event(struct perf_event *event) if (has_branch_stack(event)) dec = true; - if (dec) - static_key_slow_dec_deferred(&perf_sched_events); + if (dec) { + if (!atomic_add_unless(&perf_sched_count, -1, 1)) + schedule_delayed_work(&perf_sched_work, HZ); + } unaccount_event_cpu(event, event->cpu); } +static void perf_sched_delayed(struct work_struct *work) +{ + mutex_lock(&perf_sched_mutex); + if (atomic_dec_and_test(&perf_sched_count)) + static_branch_disable(&perf_sched_events); + mutex_unlock(&perf_sched_mutex); +} + /* * The following implement mutual exclusion of events on "exclusive" pmus * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled @@ -7780,8 +7796,28 @@ static void account_event(struct perf_event *event) if (is_cgroup_event(event)) inc = true; - if (inc) - static_key_slow_inc(&perf_sched_events.key); + if (inc) { + if (atomic_inc_not_zero(&perf_sched_count)) + goto enabled; + + mutex_lock(&perf_sched_mutex); + if (!atomic_read(&perf_sched_count)) { + static_branch_enable(&perf_sched_events); + /* + * Guarantee that all CPUs observe they key change and + * call the perf scheduling hooks before proceeding to + * install events that need them. + */ + synchronize_sched(); + } + /* + * Now that we have waited for the sync_sched(), allow further + * increments to by-pass the mutex. + */ + atomic_inc(&perf_sched_count); + mutex_unlock(&perf_sched_mutex); + } +enabled: account_event_cpu(event, event->cpu); } @@ -9344,9 +9380,6 @@ void __init perf_event_init(void) ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); - /* do not patch jump label more than once per second */ - jump_label_rate_limit(&perf_sched_events, HZ); - /* * Build time assertion that we keep the data_head at the intended * location. IOW, validation we got the __reserved[] size right. From 28a967c3a2f99fa3b5f762f25cb2a319d933571b Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:46 +0100 Subject: [PATCH 457/489] perf: Cure event->pending_disable race Because event_sched_out() checks event->pending_disable _before_ actually disabling the event, it can happen that the event fires after it checks but before it gets disabled. This would leave event->pending_disable set and the queued irq_work will try and process it. However, if the event trigger was during schedule(), the event might have been de-scheduled by the time the irq_work runs, and perf_event_disable_local() will fail. Fix this by checking event->pending_disable _after_ we call event->pmu->del(). This depends on the latter being a compiler barrier, such that the compiler does not lift the load and re-creates the problem. Tested-by: Alexander Shishkin Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.040469884@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index ea064ca8dd3c..de14b67a3b0b 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1696,14 +1696,14 @@ event_sched_out(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_stopped = tstamp; + event->pmu->del(event, 0); + event->oncpu = -1; event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; event->state = PERF_EVENT_STATE_OFF; } - event->tstamp_stopped = tstamp; - event->pmu->del(event, 0); - event->oncpu = -1; if (!is_software_event(event)) cpuctx->active_oncpu--; From 3cbaa59069677920186dcf502632ca1df4329f80 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:47 +0100 Subject: [PATCH 458/489] perf: Fix ctx time tracking by introducing EVENT_TIME Currently any ctx_sched_in() call will re-start the ctx time tracking, this means that calls like: ctx_sched_in(.event_type = EVENT_PINNED); ctx_sched_in(.event_type = EVENT_FLEXIBLE); will have a hole in their ctx time tracking. This is likely harmless but can confuse things a little. By adding EVENT_TIME, we can have the first ctx_sched_in() (is_active: 0 -> !0) start the time and any further ctx_sched_in() will leave the timestamps alone. Secondly, this allows for an early disable like: ctx_sched_out(.event_type = EVENT_TIME); which would update the ctx time (if the ctx is active) and any further calls to ctx_sched_out() would not further modify the ctx time. For ctx_sched_in() any 0 -> !0 transition will automatically include EVENT_TIME. For ctx_sched_out(), any transition that clears EVENT_ALL will automatically clear EVENT_TIME. These two rules ensure that under normal circumstances we need not bother with EVENT_TIME and get natural ctx time behaviour. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.100446561@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 42 ++++++++++++++++++++++++++++++------------ 1 file changed, 30 insertions(+), 12 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index de14b67a3b0b..75bde93eb76f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -314,6 +314,7 @@ again: enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, + EVENT_TIME = 0x4, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; @@ -1294,16 +1295,18 @@ static u64 perf_event_time(struct perf_event *event) /* * Update the total_time_enabled and total_time_running fields for a event. - * The caller of this function needs to hold the ctx->lock. */ static void update_event_times(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; u64 run_end; + lockdep_assert_held(&ctx->lock); + if (event->state < PERF_EVENT_STATE_INACTIVE || event->group_leader->state < PERF_EVENT_STATE_INACTIVE) return; + /* * in cgroup mode, time_enabled represents * the time the event was enabled AND active @@ -2349,24 +2352,33 @@ static void ctx_sched_out(struct perf_event_context *ctx, } ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); if (!ctx->is_active) cpuctx->task_ctx = NULL; } - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); - if (!ctx->nr_active) + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* update (and stop) ctx time */ + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); + } + + if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; perf_pmu_disable(ctx->pmu); - if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { + if (is_active & EVENT_PINNED) { list_for_each_entry(event, &ctx->pinned_groups, group_entry) group_sched_out(event, cpuctx, ctx); } - if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { + if (is_active & EVENT_FLEXIBLE) { list_for_each_entry(event, &ctx->flexible_groups, group_entry) group_sched_out(event, cpuctx, ctx); } @@ -2740,7 +2752,7 @@ ctx_sched_in(struct perf_event_context *ctx, if (likely(!ctx->nr_events)) return; - ctx->is_active |= event_type; + ctx->is_active |= (event_type | EVENT_TIME); if (ctx->task) { if (!is_active) cpuctx->task_ctx = ctx; @@ -2748,18 +2760,24 @@ ctx_sched_in(struct perf_event_context *ctx, WARN_ON_ONCE(cpuctx->task_ctx != ctx); } - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* start ctx time */ + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); + } + /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) + if (is_active & EVENT_PINNED) ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ - if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) + if (is_active & EVENT_FLEXIBLE) ctx_flexible_sched_in(ctx, cpuctx); } From 7fce250915efca0f8f51dddee3ae89bf30d86ca5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:48 +0100 Subject: [PATCH 459/489] perf: Fix scaling vs. perf_event_enable_on_exec() The recent commit 3e349507d12d ("perf: Fix perf_enable_on_exec() event scheduling") caused this by moving task_ctx_sched_out() from before __perf_event_mask_enable() to after it. The overlooked consequence of that change is that task_ctx_sched_out() would update the ctx time fields, and now __perf_event_mask_enable() uses stale time. In order to fix this, explicitly stop our context's time before enabling the event(s). Reported-by: Oleg Nesterov Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Fixes: 3e349507d12d ("perf: Fix perf_enable_on_exec() event scheduling") Link: http://lkml.kernel.org/r/20160224174948.159242158@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 75bde93eb76f..d0030886c402 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3143,6 +3143,7 @@ static void perf_event_enable_on_exec(int ctxn) cpuctx = __get_cpu_context(ctx); perf_ctx_lock(cpuctx, ctx); + ctx_sched_out(ctx, cpuctx, EVENT_TIME); list_for_each_entry(event, &ctx->event_list, event_entry) enabled |= event_enable_on_exec(event, ctx); From bd2afa49d194c6412c333e9fdd48bc5d06bb465d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:49 +0100 Subject: [PATCH 460/489] perf: Fix scaling vs. perf_event_enable() Similar to the perf_enable_on_exec(), ensure that event timings are consistent across perf_event_enable(). Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.218288698@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index d0030886c402..57c25faecfa5 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2069,14 +2069,27 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx); +static void ctx_sched_out(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type); static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type, struct task_struct *task); +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (!cpuctx->task_ctx) + return; + + if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) + return; + + ctx_sched_out(ctx, cpuctx, EVENT_ALL); +} + static void perf_event_sched_in(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, struct task_struct *task) @@ -2227,17 +2240,18 @@ static void __perf_event_enable(struct perf_event *event, event->state <= PERF_EVENT_STATE_ERROR) return; - update_context_time(ctx); + if (ctx->is_active) + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + __perf_event_mark_enabled(event); if (!ctx->is_active) return; if (!event_filter_match(event)) { - if (is_cgroup_event(event)) { - perf_cgroup_set_timestamp(current, ctx); // XXX ? + if (is_cgroup_event(event)) perf_cgroup_defer_enabled(event); - } + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; } @@ -2245,8 +2259,10 @@ static void __perf_event_enable(struct perf_event *event, * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. */ - if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) + if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); return; + } task_ctx = cpuctx->task_ctx; if (ctx->task) @@ -2658,18 +2674,6 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task, next); } -static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - if (!cpuctx->task_ctx) - return; - - if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) - return; - - ctx_sched_out(ctx, cpuctx, EVENT_ALL); -} - /* * Called with IRQs disabled */ From a096309bc4677f60caa8e93fcc613a55073c51d4 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:50 +0100 Subject: [PATCH 461/489] perf: Fix scaling vs. perf_install_in_context() Completely reworks perf_install_in_context() (again!) in order to ensure that there will be no ctx time hole between add_event_to_ctx() and any potential ctx_sched_in(). Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.279399438@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 127 ++++++++++++++++++++++++++----------------- 1 file changed, 76 insertions(+), 51 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 57c25faecfa5..25edabd207de 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -276,10 +276,10 @@ static void event_function_call(struct perf_event *event, event_f func, void *da return; } -again: if (task == TASK_TOMBSTONE) return; +again: if (!task_function_call(task, event_function, &efs)) return; @@ -289,13 +289,15 @@ again: * a concurrent perf_event_context_sched_out(). */ task = ctx->task; - if (task != TASK_TOMBSTONE) { - if (ctx->is_active) { - raw_spin_unlock_irq(&ctx->lock); - goto again; - } - func(event, NULL, ctx, data); + if (task == TASK_TOMBSTONE) { + raw_spin_unlock_irq(&ctx->lock); + return; } + if (ctx->is_active) { + raw_spin_unlock_irq(&ctx->lock); + goto again; + } + func(event, NULL, ctx, data); raw_spin_unlock_irq(&ctx->lock); } @@ -2116,49 +2118,68 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, /* * Cross CPU call to install and enable a performance event * - * Must be called with ctx->mutex held + * Very similar to remote_function() + event_function() but cannot assume that + * things like ctx->is_active and cpuctx->task_ctx are set. */ static int __perf_install_in_context(void *info) { - struct perf_event_context *ctx = info; + struct perf_event *event = info; + struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; + bool activate = true; + int ret = 0; raw_spin_lock(&cpuctx->ctx.lock); if (ctx->task) { raw_spin_lock(&ctx->lock); - /* - * If we hit the 'wrong' task, we've since scheduled and - * everything should be sorted, nothing to do! - */ task_ctx = ctx; - if (ctx->task != current) + + /* If we're on the wrong CPU, try again */ + if (task_cpu(ctx->task) != smp_processor_id()) { + ret = -ESRCH; goto unlock; + } /* - * If task_ctx is set, it had better be to us. + * If we're on the right CPU, see if the task we target is + * current, if not we don't have to activate the ctx, a future + * context switch will do that for us. */ - WARN_ON_ONCE(cpuctx->task_ctx != ctx && cpuctx->task_ctx); + if (ctx->task != current) + activate = false; + else + WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); + } else if (task_ctx) { raw_spin_lock(&task_ctx->lock); } - ctx_resched(cpuctx, task_ctx); + if (activate) { + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + add_event_to_ctx(event, ctx); + ctx_resched(cpuctx, task_ctx); + } else { + add_event_to_ctx(event, ctx); + } + unlock: perf_ctx_unlock(cpuctx, task_ctx); - return 0; + return ret; } /* - * Attach a performance event to a context + * Attach a performance event to a context. + * + * Very similar to event_function_call, see comment there. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { - struct task_struct *task = NULL; + struct task_struct *task = READ_ONCE(ctx->task); lockdep_assert_held(&ctx->mutex); @@ -2166,42 +2187,46 @@ perf_install_in_context(struct perf_event_context *ctx, if (event->cpu != -1) event->cpu = cpu; - /* - * Installing events is tricky because we cannot rely on ctx->is_active - * to be set in case this is the nr_events 0 -> 1 transition. - * - * So what we do is we add the event to the list here, which will allow - * a future context switch to DTRT and then send a racy IPI. If the IPI - * fails to hit the right task, this means a context switch must have - * happened and that will have taken care of business. - */ - raw_spin_lock_irq(&ctx->lock); - task = ctx->task; - - /* - * If between ctx = find_get_context() and mutex_lock(&ctx->mutex) the - * ctx gets destroyed, we must not install an event into it. - * - * This is normally tested for after we acquire the mutex, so this is - * a sanity check. - */ - if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { - raw_spin_unlock_irq(&ctx->lock); + if (!task) { + cpu_function_call(cpu, __perf_install_in_context, event); return; } - if (ctx->is_active) { - update_context_time(ctx); - update_cgrp_time_from_event(event); + /* + * Should not happen, we validate the ctx is still alive before calling. + */ + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) + return; + + /* + * Installing events is tricky because we cannot rely on ctx->is_active + * to be set in case this is the nr_events 0 -> 1 transition. + */ +again: + /* + * Cannot use task_function_call() because we need to run on the task's + * CPU regardless of whether its current or not. + */ + if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + task = ctx->task; + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { + /* + * Cannot happen because we already checked above (which also + * cannot happen), and we hold ctx->mutex, which serializes us + * against perf_event_exit_task_context(). + */ + raw_spin_unlock_irq(&ctx->lock); + return; } - - add_event_to_ctx(event, ctx); raw_spin_unlock_irq(&ctx->lock); - - if (task) - task_function_call(task, __perf_install_in_context, ctx); - else - cpu_function_call(cpu, __perf_install_in_context, ctx); + /* + * Since !ctx->is_active doesn't mean anything, we must IPI + * unconditionally. + */ + goto again; } /* From 0da4cf3e0a68c97ef811569804616a811f786729 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Feb 2016 18:45:51 +0100 Subject: [PATCH 462/489] perf: Robustify task_function_call() Since there is no serialization between task_function_call() doing task_curr() and the other CPU doing context switches, we could end up not sending an IPI even if we had to. And I'm not sure I still buy my own argument we're OK. Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: dvyukov@google.com Cc: eranian@google.com Cc: oleg@redhat.com Cc: panand@redhat.com Cc: sasha.levin@oracle.com Cc: vince@deater.net Link: http://lkml.kernel.org/r/20160224174948.340031200@infradead.org Signed-off-by: Ingo Molnar --- kernel/events/core.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 25edabd207de..614614821f00 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -64,8 +64,17 @@ static void remote_function(void *data) struct task_struct *p = tfc->p; if (p) { - tfc->ret = -EAGAIN; - if (task_cpu(p) != smp_processor_id() || !task_curr(p)) + /* -EAGAIN */ + if (task_cpu(p) != smp_processor_id()) + return; + + /* + * Now that we're on right CPU with IRQs disabled, we can test + * if we hit the right task without races. + */ + + tfc->ret = -ESRCH; /* No such (running) process */ + if (p != current) return; } @@ -92,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) .p = p, .func = func, .info = info, - .ret = -ESRCH, /* No such (running) process */ + .ret = -EAGAIN, }; + int ret; - if (task_curr(p)) - smp_call_function_single(task_cpu(p), remote_function, &data, 1); + do { + ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); + if (!ret) + ret = data.ret; + } while (ret == -EAGAIN); - return data.ret; + return ret; } /** @@ -169,19 +182,6 @@ static bool is_kernel_event(struct perf_event *event) * rely on ctx->is_active and therefore cannot use event_function_call(). * See perf_install_in_context(). * - * This is because we need a ctx->lock serialized variable (ctx->is_active) - * to reliably determine if a particular task/context is scheduled in. The - * task_curr() use in task_function_call() is racy in that a remote context - * switch is not a single atomic operation. - * - * As is, the situation is 'safe' because we set rq->curr before we do the - * actual context switch. This means that task_curr() will fail early, but - * we'll continue spinning on ctx->is_active until we've passed - * perf_event_task_sched_out(). - * - * Without this ctx->lock serialized variable we could have race where we find - * the task (and hence the context) would not be active while in fact they are. - * * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. */ @@ -212,7 +212,7 @@ static int event_function(void *info) */ if (ctx->task) { if (ctx->task != current) { - ret = -EAGAIN; + ret = -ESRCH; goto unlock; } From 3b43b71f05d3ecd01c4116254666d9492301697d Mon Sep 17 00:00:00 2001 From: Kai-Heng Feng Date: Thu, 25 Feb 2016 15:19:38 +0800 Subject: [PATCH 463/489] ALSA: hda - Fixing background noise on Dell Inspiron 3162 After login to the desktop on Dell Inspiron 3162, there's a very loud background noise comes from the builtin speaker. The noise does not go away even if the speaker is muted. The noise disappears after using the aamix fixup. Codec: Realtek ALC3234 Address: 0 AFG Function Id: 0x1 (unsol 1) Vendor Id: 0x10ec0255 Subsystem Id: 0x10280725 Revision Id: 0x100002 No Modem Function Group found BugLink: http://bugs.launchpad.net/bugs/1549620 Signed-off-by: Kai-Heng Feng Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index efd4980cffb8..72fa58dd7723 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4749,6 +4749,7 @@ enum { ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, + ALC255_FIXUP_DELL_SPK_NOISE, }; static const struct hda_fixup alc269_fixups[] = { @@ -5368,6 +5369,12 @@ static const struct hda_fixup alc269_fixups[] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_fixup_lenovo_line2_mic_hotkey, }, + [ALC255_FIXUP_DELL_SPK_NOISE] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5410,6 +5417,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1028, 0x06df, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x06e0, "Dell", ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK), SND_PCI_QUIRK(0x1028, 0x0704, "Dell XPS 13", ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE), + SND_PCI_QUIRK(0x1028, 0x0725, "Dell Inspiron 3162", ALC255_FIXUP_DELL_SPK_NOISE), SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2), From 17e4bce0ae63c7e03f3c7fa8d80890e7af3d4971 Mon Sep 17 00:00:00 2001 From: Mike Krinkin Date: Wed, 24 Feb 2016 21:02:31 +0300 Subject: [PATCH 464/489] KVM: x86: MMU: fix ubsan index-out-of-range warning Ubsan reports the following warning due to a typo in update_accessed_dirty_bits template, the patch fixes the typo: [ 168.791851] ================================================================================ [ 168.791862] UBSAN: Undefined behaviour in arch/x86/kvm/paging_tmpl.h:252:15 [ 168.791866] index 4 is out of range for type 'u64 [4]' [ 168.791871] CPU: 0 PID: 2950 Comm: qemu-system-x86 Tainted: G O L 4.5.0-rc5-next-20160222 #7 [ 168.791873] Hardware name: LENOVO 23205NG/23205NG, BIOS G2ET95WW (2.55 ) 07/09/2013 [ 168.791876] 0000000000000000 ffff8801cfcaf208 ffffffff81c9f780 0000000041b58ab3 [ 168.791882] ffffffff82eb2cc1 ffffffff81c9f6b4 ffff8801cfcaf230 ffff8801cfcaf1e0 [ 168.791886] 0000000000000004 0000000000000001 0000000000000000 ffffffffa1981600 [ 168.791891] Call Trace: [ 168.791899] [] dump_stack+0xcc/0x12c [ 168.791904] [] ? _atomic_dec_and_lock+0xc4/0xc4 [ 168.791910] [] ubsan_epilogue+0xd/0x8a [ 168.791914] [] __ubsan_handle_out_of_bounds+0x15c/0x1a3 [ 168.791918] [] ? __ubsan_handle_shift_out_of_bounds+0x2bd/0x2bd [ 168.791922] [] ? get_user_pages_fast+0x2bf/0x360 [ 168.791954] [] ? kvm_largepages_enabled+0x30/0x30 [kvm] [ 168.791958] [] ? __get_user_pages_fast+0x360/0x360 [ 168.791987] [] paging64_walk_addr_generic+0x1b28/0x2600 [kvm] [ 168.792014] [] ? init_kvm_mmu+0x1100/0x1100 [kvm] [ 168.792019] [] ? debug_check_no_locks_freed+0x350/0x350 [ 168.792044] [] ? init_kvm_mmu+0x1100/0x1100 [kvm] [ 168.792076] [] paging64_gva_to_gpa+0x7d/0x110 [kvm] [ 168.792121] [] ? paging64_walk_addr_generic+0x2600/0x2600 [kvm] [ 168.792130] [] ? debug_lockdep_rcu_enabled+0x7b/0x90 [ 168.792178] [] emulator_read_write_onepage+0x27a/0x1150 [kvm] [ 168.792208] [] ? __kvm_read_guest_page+0x54/0x70 [kvm] [ 168.792234] [] ? kvm_task_switch+0x160/0x160 [kvm] [ 168.792238] [] ? debug_lockdep_rcu_enabled+0x7b/0x90 [ 168.792263] [] emulator_read_write+0xe7/0x6d0 [kvm] [ 168.792290] [] ? em_cr_write+0x230/0x230 [kvm] [ 168.792314] [] emulator_write_emulated+0x15/0x20 [kvm] [ 168.792340] [] segmented_write+0xf8/0x130 [kvm] [ 168.792367] [] ? em_lgdt+0x20/0x20 [kvm] [ 168.792374] [] ? vmx_read_guest_seg_ar+0x42/0x1e0 [kvm_intel] [ 168.792400] [] writeback+0x3f2/0x700 [kvm] [ 168.792424] [] ? em_sidt+0xa0/0xa0 [kvm] [ 168.792449] [] ? x86_decode_insn+0x1b3d/0x4f70 [kvm] [ 168.792474] [] x86_emulate_insn+0x572/0x3010 [kvm] [ 168.792499] [] x86_emulate_instruction+0x3bd/0x2110 [kvm] [ 168.792524] [] ? reexecute_instruction.part.110+0x2e0/0x2e0 [kvm] [ 168.792532] [] handle_ept_misconfig+0x61/0x460 [kvm_intel] [ 168.792539] [] ? handle_pause+0x450/0x450 [kvm_intel] [ 168.792546] [] vmx_handle_exit+0xd6a/0x1ad0 [kvm_intel] [ 168.792572] [] ? kvm_arch_vcpu_ioctl_run+0xbdc/0x6090 [kvm] [ 168.792597] [] kvm_arch_vcpu_ioctl_run+0xd3d/0x6090 [kvm] [ 168.792621] [] ? kvm_arch_vcpu_ioctl_run+0xbdc/0x6090 [kvm] [ 168.792627] [] ? __ww_mutex_lock_interruptible+0x1630/0x1630 [ 168.792651] [] ? kvm_arch_vcpu_runnable+0x4f0/0x4f0 [kvm] [ 168.792656] [] ? preempt_notifier_unregister+0x190/0x190 [ 168.792681] [] ? kvm_arch_vcpu_load+0x127/0x650 [kvm] [ 168.792704] [] kvm_vcpu_ioctl+0x553/0xda0 [kvm] [ 168.792727] [] ? vcpu_put+0x40/0x40 [kvm] [ 168.792732] [] ? debug_check_no_locks_freed+0x350/0x350 [ 168.792735] [] ? _raw_spin_unlock+0x27/0x40 [ 168.792740] [] ? handle_mm_fault+0x1673/0x2e40 [ 168.792744] [] ? trace_hardirqs_on_caller+0x478/0x6c0 [ 168.792747] [] ? trace_hardirqs_on+0xd/0x10 [ 168.792751] [] ? debug_lockdep_rcu_enabled+0x7b/0x90 [ 168.792756] [] do_vfs_ioctl+0x1b0/0x12b0 [ 168.792759] [] ? ioctl_preallocate+0x210/0x210 [ 168.792763] [] ? __fget+0x273/0x4a0 [ 168.792766] [] ? __fget+0x50/0x4a0 [ 168.792770] [] ? __fget_light+0x96/0x2b0 [ 168.792773] [] SyS_ioctl+0x79/0x90 [ 168.792777] [] entry_SYSCALL_64_fastpath+0x23/0xc1 [ 168.792780] ================================================================================ Signed-off-by: Mike Krinkin Reviewed-by: Xiao Guangrong Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/kvm/paging_tmpl.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 6c9fed957cce..2ce4f05e81d3 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -249,7 +249,7 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, return ret; kvm_vcpu_mark_page_dirty(vcpu, table_gfn); - walker->ptes[level] = pte; + walker->ptes[level - 1] = pte; } return 0; } From 2ae955774f29bbd7d16149cb0ae8d0319bf2ecc4 Mon Sep 17 00:00:00 2001 From: David Henningsson Date: Thu, 25 Feb 2016 09:37:05 +0100 Subject: [PATCH 465/489] ALSA: hda - Fixup speaker pass-through control for nid 0x14 on ALC225 On one of the machines we enable, we found that the actual speaker volume did not always correspond to the volume set in alsamixer. This patch fixes that problem. This patch was orginally written by Kailang @ Realtek, I've rebased it to fit sound git master. Cc: stable@vger.kernel.org BugLink: https://bugs.launchpad.net/bugs/1549660 Co-Authored-By: Kailang Signed-off-by: David Henningsson Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 72fa58dd7723..7fded69fb58e 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -3801,6 +3801,10 @@ static void alc_headset_mode_mic_in(struct hda_codec *codec, hda_nid_t hp_pin, static void alc_headset_mode_default(struct hda_codec *codec) { + static struct coef_fw coef0225[] = { + UPDATE_COEF(0x45, 0x3f<<10, 0x34<<10), + {} + }; static struct coef_fw coef0255[] = { WRITE_COEF(0x45, 0xc089), WRITE_COEF(0x45, 0xc489), @@ -3842,6 +3846,9 @@ static void alc_headset_mode_default(struct hda_codec *codec) }; switch (codec->core.vendor_id) { + case 0x10ec0225: + alc_process_coef_fw(codec, coef0225); + break; case 0x10ec0255: case 0x10ec0256: alc_process_coef_fw(codec, coef0255); @@ -4750,6 +4757,7 @@ enum { ALC293_FIXUP_LENOVO_SPK_NOISE, ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, + ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, }; static const struct hda_fixup alc269_fixups[] = { @@ -5375,6 +5383,17 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE }, + [ALC225_FIXUP_DELL1_MIC_NO_PRESENCE] = { + .type = HDA_FIXUP_VERBS, + .v.verbs = (const struct hda_verb[]) { + /* Disable pass-through path for FRONT 14h */ + { 0x20, AC_VERB_SET_COEF_INDEX, 0x36 }, + { 0x20, AC_VERB_SET_PROC_COEF, 0x57d7 }, + {} + }, + .chained = true, + .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5646,10 +5665,10 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {0x21, 0x03211020} static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { - SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x14, 0x901701a0}), - SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, + SND_HDA_PIN_QUIRK(0x10ec0225, 0x1028, "Dell", ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, ALC225_STANDARD_PINS, {0x14, 0x901701b0}), SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, From f883982dc1b117f04579f0896821cd9f2e397f94 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Thu, 25 Feb 2016 14:31:59 +0100 Subject: [PATCH 466/489] ALSA: hda - Fix headset support and noise on HP EliteBook 755 G2 HP EliteBook 755 G2 with ALC3228 (ALC280) codec [103c:221c] requires the known fixup (ALC269_FIXUP_HEADSET_MIC) for making the headset mic working. Also, it suffers from the loopback noise problem, so we should disable aamix path as well. Reported-by: Derick Eddington Cc: Signed-off-by: Takashi Iwai --- sound/pci/hda/patch_realtek.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 7fded69fb58e..1f357cd72d9c 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -4758,6 +4758,7 @@ enum { ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, ALC255_FIXUP_DELL_SPK_NOISE, ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, + ALC280_FIXUP_HP_HEADSET_MIC, }; static const struct hda_fixup alc269_fixups[] = { @@ -5394,6 +5395,12 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE }, + [ALC280_FIXUP_HP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_disable_aamix, + .chained = true, + .chain_id = ALC269_FIXUP_HEADSET_MIC, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -5497,6 +5504,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x2335, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2336, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), SND_PCI_QUIRK(0x103c, 0x2337, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1), + SND_PCI_QUIRK(0x103c, 0x221c, "HP EliteBook 755 G2", ALC280_FIXUP_HP_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), From bf70e5513dfea29c3682e7eb3dbb45f0723bac09 Mon Sep 17 00:00:00 2001 From: Dexuan Cui Date: Thu, 25 Feb 2016 01:58:12 -0800 Subject: [PATCH 467/489] x86/mm: Fix slow_virt_to_phys() for X86_PAE again "d1cd12108346: x86, pageattr: Prevent overflow in slow_virt_to_phys() for X86_PAE" was unintentionally removed by the recent "34437e67a672: x86/mm: Fix slow_virt_to_phys() to handle large PAT bit". And, the variable 'phys_addr' was defined as "unsigned long" by mistake -- it should be "phys_addr_t". As a result, Hyper-V network driver in 32-PAE Linux guest can't work again. Fixes: commit 34437e67a672: "x86/mm: Fix slow_virt_to_phys() to handle large PAT bit" Signed-off-by: Dexuan Cui Reviewed-by: Toshi Kani Cc: olaf@aepfle.de Cc: gregkh@linuxfoundation.org Cc: jasowang@redhat.com Cc: driverdev-devel@linuxdriverproject.org Cc: linux-mm@kvack.org Cc: apw@canonical.com Cc: Andrew Morton Cc: K. Y. Srinivasan Cc: Haiyang Zhang Link: http://lkml.kernel.org/r/1456394292-9030-1-git-send-email-decui@microsoft.com Signed-off-by: Thomas Gleixner --- arch/x86/mm/pageattr.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 2440814b0069..9cf96d82147a 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -419,24 +419,30 @@ pmd_t *lookup_pmd_address(unsigned long address) phys_addr_t slow_virt_to_phys(void *__virt_addr) { unsigned long virt_addr = (unsigned long)__virt_addr; - unsigned long phys_addr, offset; + phys_addr_t phys_addr; + unsigned long offset; enum pg_level level; pte_t *pte; pte = lookup_address(virt_addr, &level); BUG_ON(!pte); + /* + * pXX_pfn() returns unsigned long, which must be cast to phys_addr_t + * before being left-shifted PAGE_SHIFT bits -- this trick is to + * make 32-PAE kernel work correctly. + */ switch (level) { case PG_LEVEL_1G: - phys_addr = pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pud_pfn(*(pud_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PUD_PAGE_MASK; break; case PG_LEVEL_2M: - phys_addr = pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pmd_pfn(*(pmd_t *)pte) << PAGE_SHIFT; offset = virt_addr & ~PMD_PAGE_MASK; break; default: - phys_addr = pte_pfn(*pte) << PAGE_SHIFT; + phys_addr = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT; offset = virt_addr & ~PAGE_MASK; } From 473f414564528a819f0c2bb6b4bf26366b64c9ab Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Tue, 23 Feb 2016 15:54:47 +0100 Subject: [PATCH 468/489] ALSA: hda - Loop interrupt handling until really cleared Currently the interrupt handler of HD-audio driver assumes that no irq update is needed while processing the irq. But in reality, it has been confirmed that the HW irq is issued even during the irq handling. Since we clear the irq status at the beginning, process the interrupt, then exits from the handler, the lately issued interrupt is left untouched without being properly processed. This patch changes the interrupt handler code to loop over the check-and-process. The handler tries repeatedly as long as the IRQ status are turned on, and either stream or CORB/RIRB is handled. For checking the stream handling, snd_hdac_bus_handle_stream_irq() returns a value indicating the stream indices bits. Other than that, the change is only in the irq handler itself. Reported-by: Libin Yang Cc: Signed-off-by: Takashi Iwai --- include/sound/hdaudio.h | 2 +- sound/hda/hdac_controller.c | 7 +++++- sound/pci/hda/hda_controller.c | 45 +++++++++++++++++++--------------- 3 files changed, 32 insertions(+), 22 deletions(-) diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h index e2b712c90d3f..c21c38ce7450 100644 --- a/include/sound/hdaudio.h +++ b/include/sound/hdaudio.h @@ -343,7 +343,7 @@ void snd_hdac_bus_enter_link_reset(struct hdac_bus *bus); void snd_hdac_bus_exit_link_reset(struct hdac_bus *bus); void snd_hdac_bus_update_rirb(struct hdac_bus *bus); -void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, +int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, void (*ack)(struct hdac_bus *, struct hdac_stream *)); diff --git a/sound/hda/hdac_controller.c b/sound/hda/hdac_controller.c index b5a17cb510a0..8c486235c905 100644 --- a/sound/hda/hdac_controller.c +++ b/sound/hda/hdac_controller.c @@ -426,18 +426,22 @@ EXPORT_SYMBOL_GPL(snd_hdac_bus_stop_chip); * @bus: HD-audio core bus * @status: INTSTS register value * @ask: callback to be called for woken streams + * + * Returns the bits of handled streams, or zero if no stream is handled. */ -void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, +int snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, void (*ack)(struct hdac_bus *, struct hdac_stream *)) { struct hdac_stream *azx_dev; u8 sd_status; + int handled = 0; list_for_each_entry(azx_dev, &bus->stream_list, list) { if (status & azx_dev->sd_int_sta_mask) { sd_status = snd_hdac_stream_readb(azx_dev, SD_STS); snd_hdac_stream_writeb(azx_dev, SD_STS, SD_INT_MASK); + handled |= 1 << azx_dev->index; if (!azx_dev->substream || !azx_dev->running || !(sd_status & SD_INT_COMPLETE)) continue; @@ -445,6 +449,7 @@ void snd_hdac_bus_handle_stream_irq(struct hdac_bus *bus, unsigned int status, ack(bus, azx_dev); } } + return handled; } EXPORT_SYMBOL_GPL(snd_hdac_bus_handle_stream_irq); diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index 37cf9cee9835..27de8015717d 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -930,6 +930,8 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) struct azx *chip = dev_id; struct hdac_bus *bus = azx_bus(chip); u32 status; + bool active, handled = false; + int repeat = 0; /* count for avoiding endless loop */ #ifdef CONFIG_PM if (azx_has_pm_runtime(chip)) @@ -939,33 +941,36 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) spin_lock(&bus->reg_lock); - if (chip->disabled) { - spin_unlock(&bus->reg_lock); - return IRQ_NONE; - } + if (chip->disabled) + goto unlock; - status = azx_readl(chip, INTSTS); - if (status == 0 || status == 0xffffffff) { - spin_unlock(&bus->reg_lock); - return IRQ_NONE; - } + do { + status = azx_readl(chip, INTSTS); + if (status == 0 || status == 0xffffffff) + break; - snd_hdac_bus_handle_stream_irq(bus, status, stream_update); + handled = true; + active = false; + if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update)) + active = true; - /* clear rirb int */ - status = azx_readb(chip, RIRBSTS); - if (status & RIRB_INT_MASK) { - if (status & RIRB_INT_RESPONSE) { - if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) - udelay(80); - snd_hdac_bus_update_rirb(bus); + /* clear rirb int */ + status = azx_readb(chip, RIRBSTS); + if (status & RIRB_INT_MASK) { + active = true; + if (status & RIRB_INT_RESPONSE) { + if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) + udelay(80); + snd_hdac_bus_update_rirb(bus); + } + azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); } - azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); - } + } while (active && ++repeat < 10); + unlock: spin_unlock(&bus->reg_lock); - return IRQ_HANDLED; + return IRQ_RETVAL(handled); } EXPORT_SYMBOL_GPL(azx_interrupt); From 9bf148cb0812595bfdf5100bd2c07e9bec9c6ef5 Mon Sep 17 00:00:00 2001 From: Colin Ian King Date: Fri, 26 Feb 2016 18:55:31 +0000 Subject: [PATCH 469/489] x86/mpx: Fix off-by-one comparison with nr_registers In the unlikely event that regno == nr_registers then we get an array overrun on regoff because the invalid register check is currently off-by-one. Fix this with a check that regno is >= nr_registers instead. Detected with static analysis using CoverityScan. Fixes: fcc7ffd67991 "x86, mpx: Decode MPX instruction to get bound violation information" Signed-off-by: Colin Ian King Acked-by: Dave Hansen Cc: Borislav Petkov Cc: "Kirill A . Shutemov" Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/1456512931-3388-1-git-send-email-colin.king@canonical.com Signed-off-by: Thomas Gleixner --- arch/x86/mm/mpx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c index b2fd67da1701..ef05755a1900 100644 --- a/arch/x86/mm/mpx.c +++ b/arch/x86/mm/mpx.c @@ -123,7 +123,7 @@ static int get_reg_offset(struct insn *insn, struct pt_regs *regs, break; } - if (regno > nr_registers) { + if (regno >= nr_registers) { WARN_ONCE(1, "decoded an instruction with an invalid register"); return -EINVAL; } From 6c777e8799a93e3bdb67bec622429e1b48dc90fb Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 17 Feb 2016 12:26:42 -0600 Subject: [PATCH 470/489] Revert "PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") appeared in v4.3 and helps support IOAPIC hotplug. Олег reported that the Elcus-1553 TA1-PCI driver worked in v4.2 but not v4.3 and bisected it to 991de2e59090. Sunjin reported that the RocketRAID 272x driver worked in v4.2 but not v4.3. In both cases booting with "pci=routirq" is a workaround. I think the problem is that after 991de2e59090, we no longer call pcibios_enable_irq() for upstream bridges. Prior to 991de2e59090, when a driver called pci_enable_device(), we recursively called pcibios_enable_irq() for upstream bridges via pci_enable_bridge(). After 991de2e59090, we call pcibios_enable_irq() from pci_device_probe() instead of the pci_enable_device() path, which does *not* call pcibios_enable_irq() for upstream bridges. Revert 991de2e59090 to fix these driver regressions. Link: https://bugzilla.kernel.org/show_bug.cgi?id=111211 Fixes: 991de2e59090 ("PCI, x86: Implement pcibios_alloc_irq() and pcibios_free_irq()") Reported-and-tested-by: Олег Мороз Reported-by: Sunjin Yang Signed-off-by: Bjorn Helgaas Acked-by: Rafael J. Wysocki CC: Jiang Liu --- arch/x86/include/asm/pci_x86.h | 2 ++ arch/x86/pci/common.c | 26 ++++++++++++++------------ arch/x86/pci/intel_mid_pci.c | 7 ++----- arch/x86/pci/irq.c | 15 ++++++++++++++- drivers/acpi/pci_irq.c | 9 ++++++++- 5 files changed, 40 insertions(+), 19 deletions(-) diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 46873fbd44e1..d08eacd298c2 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock; extern int (*pcibios_enable_irq)(struct pci_dev *dev); extern void (*pcibios_disable_irq)(struct pci_dev *dev); +extern bool mp_should_keep_irq(struct device *dev); + struct pci_raw_ops { int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val); diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c index cb499c5b6ae5..d34b5118b4e8 100644 --- a/arch/x86/pci/common.c +++ b/arch/x86/pci/common.c @@ -711,20 +711,22 @@ int pcibios_add_device(struct pci_dev *dev) return 0; } -int pcibios_alloc_irq(struct pci_dev *dev) -{ - return pcibios_enable_irq(dev); -} - -void pcibios_free_irq(struct pci_dev *dev) -{ - if (pcibios_disable_irq) - pcibios_disable_irq(dev); -} - int pcibios_enable_device(struct pci_dev *dev, int mask) { - return pci_enable_resources(dev, mask); + int err; + + if ((err = pci_enable_resources(dev, mask)) < 0) + return err; + + if (!pci_dev_msi_enabled(dev)) + return pcibios_enable_irq(dev); + return 0; +} + +void pcibios_disable_device (struct pci_dev *dev) +{ + if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq) + pcibios_disable_irq(dev); } int pci_ext_cfg_avail(void) diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 8826ff593ebc..8b93e634af84 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -256,13 +256,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) static void intel_mid_pci_irq_disable(struct pci_dev *dev) { - if (dev->irq_managed && dev->irq > 0) { + if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed && + dev->irq > 0) { mp_unmap_irq(dev->irq); dev->irq_managed = 0; - /* - * Don't reset dev->irq here, otherwise - * intel_mid_pci_irq_enable() will fail on next call. - */ } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index 72108f0b66b1..9bd115484745 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -1257,9 +1257,22 @@ static int pirq_enable_irq(struct pci_dev *dev) return 0; } +bool mp_should_keep_irq(struct device *dev) +{ + if (dev->power.is_prepared) + return true; +#ifdef CONFIG_PM + if (dev->power.runtime_status == RPM_SUSPENDING) + return true; +#endif + + return false; +} + static void pirq_disable_irq(struct pci_dev *dev) { - if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) { + if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) && + dev->irq_managed && dev->irq) { mp_unmap_irq(dev->irq); dev->irq = 0; dev->irq_managed = 0; diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 9032db7e4b3a..c8e169e46673 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -478,6 +478,14 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (!pin || !dev->irq_managed || dev->irq <= 0) return; + /* Keep IOAPIC pin configuration when suspending */ + if (dev->dev.power.is_prepared) + return; +#ifdef CONFIG_PM + if (dev->dev.power.runtime_status == RPM_SUSPENDING) + return; +#endif + entry = acpi_pci_irq_lookup(dev, pin); if (!entry) return; @@ -498,6 +506,5 @@ void acpi_pci_irq_disable(struct pci_dev *dev) if (gsi >= 0) { acpi_unregister_gsi(gsi); dev->irq_managed = 0; - dev->irq = 0; } } From 61d9e854dfb91b46b99ffd3d31fc7d45d2b95f31 Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Thu, 18 Feb 2016 14:32:10 +0100 Subject: [PATCH 471/489] PCI: mvebu: Restrict build to 32-bit ARM This driver uses PCI glue that is only available on 32-bit ARM. This used to work fine as long as ARCH_MVEBU and ARCH_DOVE were exclusively 32-bit, but there's a patch in the pipe to make ARCH_MVEBU also available on 64-bit ARM. [bhelgaas: changelog; patch is coming but not merged yet] Signed-off-by: Thierry Reding Signed-off-by: Bjorn Helgaas Acked-by: Thomas Petazzoni --- drivers/pci/host/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig index 75a605426538..d1cdd9c992ac 100644 --- a/drivers/pci/host/Kconfig +++ b/drivers/pci/host/Kconfig @@ -14,6 +14,7 @@ config PCI_DRA7XX config PCI_MVEBU bool "Marvell EBU PCIe controller" depends on ARCH_MVEBU || ARCH_DOVE + depends on ARM depends on OF config PCIE_DW From ad33bb04b2a6cee6c1f99fabb15cddbf93ff0433 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Feb 2016 15:19:28 -0800 Subject: [PATCH 472/489] mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED pmd_trans_unstable()/pmd_none_or_trans_huge_or_clear_bad() were introduced to locklessy (but atomically) detect when a pmd is a regular (stable) pmd or when the pmd is unstable and can infinitely transition from pmd_none() and pmd_trans_huge() from under us, while only holding the mmap_sem for reading (for writing not). While holding the mmap_sem only for reading, MADV_DONTNEED can run from under us and so before we can assume the pmd to be a regular stable pmd we need to compare it against pmd_none() and pmd_trans_huge() in an atomic way, with pmd_trans_unstable(). The old pmd_trans_huge() left a tiny window for a race. Useful applications are unlikely to notice the difference as doing MADV_DONTNEED concurrently with a page fault would lead to undefined behavior. [akpm@linux-foundation.org: tidy up comment grammar/layout] Signed-off-by: Andrea Arcangeli Reported-by: Kirill A. Shutemov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/mm/memory.c b/mm/memory.c index 635451abc8f7..8132787ae4d5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3404,8 +3404,18 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (unlikely(pmd_none(*pmd)) && unlikely(__pte_alloc(mm, vma, pmd, address))) return VM_FAULT_OOM; - /* if an huge pmd materialized from under us just retry later */ - if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) + /* + * If a huge pmd materialized under us just retry later. Use + * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd + * didn't become pmd_trans_huge under us and then back to pmd_none, as + * a result of MADV_DONTNEED running immediately after a huge pmd fault + * in a different thread of this mm, in turn leading to a misleading + * pmd_trans_huge() retval. All we have to ensure is that it is a + * regular pmd that we can walk with pte_offset_map() and we can do that + * through an atomic read in C, which is what pmd_trans_unstable() + * provides. + */ + if (unlikely(pmd_trans_unstable(pmd) || pmd_devmap(*pmd))) return 0; /* * A regular pmd is established and it can't morph into a huge pmd From 8479eba7781fa9ffb28268840de6facfc12c35a7 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Fri, 26 Feb 2016 15:19:31 -0800 Subject: [PATCH 473/489] mm: numa: quickly fail allocations for NUMA balancing on full nodes Commit 4167e9b2cf10 ("mm: remove GFP_THISNODE") removed the GFP_THISNODE flag combination due to confusing semantics. It noted that alloc_misplaced_dst_page() was one such user after changes made by commit e97ca8e5b864 ("mm: fix GFP_THISNODE callers and clarify"). Unfortunately when GFP_THISNODE was removed, users of alloc_misplaced_dst_page() started waking kswapd and entering direct reclaim because the wrong GFP flags are cleared. The consequence is that workloads that used to fit into memory now get reclaimed which is addressed by this patch. The problem can be demonstrated with "mutilate" that exercises memcached which is software dedicated to memory object caching. The configuration uses 80% of memory and is run 3 times for varying numbers of clients. The results on a 4-socket NUMA box are mutilate 4.4.0 4.4.0 vanilla numaswap-v1 Hmean 1 8394.71 ( 0.00%) 8395.32 ( 0.01%) Hmean 4 30024.62 ( 0.00%) 34513.54 ( 14.95%) Hmean 7 32821.08 ( 0.00%) 70542.96 (114.93%) Hmean 12 55229.67 ( 0.00%) 93866.34 ( 69.96%) Hmean 21 39438.96 ( 0.00%) 85749.21 (117.42%) Hmean 30 37796.10 ( 0.00%) 50231.49 ( 32.90%) Hmean 47 18070.91 ( 0.00%) 38530.13 (113.22%) The metric is queries/second with the more the better. The results are way outside of the noise and the reason for the improvement is obvious from some of the vmstats 4.4.0 4.4.0 vanillanumaswap-v1r1 Minor Faults 1929399272 2146148218 Major Faults 19746529 3567 Swap Ins 57307366 9913 Swap Outs 50623229 17094 Allocation stalls 35909 443 DMA allocs 0 0 DMA32 allocs 72976349 170567396 Normal allocs 5306640898 5310651252 Movable allocs 0 0 Direct pages scanned 404130893 799577 Kswapd pages scanned 160230174 0 Kswapd pages reclaimed 55928786 0 Direct pages reclaimed 1843936 41921 Page writes file 2391 0 Page writes anon 50623229 17094 The vanilla kernel is swapping like crazy with large amounts of direct reclaim and kswapd activity. The figures are aggregate but it's known that the bad activity is throughout the entire test. Note that simple streaming anon/file memory consumers also see this problem but it's not as obvious. In those cases, kswapd is awake when it should not be. As there are at least two reclaim-related bugs out there, it's worth spelling out the user-visible impact. This patch only addresses bugs related to excessive reclaim on NUMA hardware when the working set is larger than a NUMA node. There is a bug related to high kswapd CPU usage but the reports are against laptops and other UMA hardware and is not addressed by this patch. Signed-off-by: Mel Gorman Cc: Vlastimil Babka Cc: Johannes Weiner Cc: David Rientjes Cc: [4.1+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/mm/migrate.c b/mm/migrate.c index b1034f9c77e7..3ad0fea5c438 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1582,7 +1582,7 @@ static struct page *alloc_misplaced_dst_page(struct page *page, (GFP_HIGHUSER_MOVABLE | __GFP_THISNODE | __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & - ~(__GFP_IO | __GFP_FS), 0); + ~__GFP_RECLAIM, 0); return newpage; } From ec9ee4acd97c0039a61c0ae4f12705767ae62153 Mon Sep 17 00:00:00 2001 From: Daniel Cashman Date: Fri, 26 Feb 2016 15:19:34 -0800 Subject: [PATCH 474/489] drivers: char: random: add get_random_long() Commit d07e22597d1d ("mm: mmap: add new /proc tunable for mmap_base ASLR") added the ability to choose from a range of values to use for entropy count in generating the random offset to the mmap_base address. The maximum value on this range was set to 32 bits for 64-bit x86 systems, but this value could be increased further, requiring more than the 32 bits of randomness provided by get_random_int(), as is already possible for arm64. Add a new function: get_random_long() which more naturally fits with the mmap usage of get_random_int() but operates exactly the same as get_random_int(). Also, fix the shifting constant in mmap_rnd() to be an unsigned long so that values greater than 31 bits generate an appropriate mask without overflow. This is especially important on x86, as its shift instruction uses a 5-bit mask for the shift operand, which meant that any value for mmap_rnd_bits over 31 acts as a no-op and effectively disables mmap_base randomization. Finally, replace calls to get_random_int() with get_random_long() where appropriate. This patch (of 2): Add get_random_long(). Signed-off-by: Daniel Cashman Acked-by: Kees Cook Cc: "Theodore Ts'o" Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Nick Kralevich Cc: Jeff Vander Stoep Cc: Mark Salyzyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/char/random.c | 22 ++++++++++++++++++++++ include/linux/random.h | 1 + 2 files changed, 23 insertions(+) diff --git a/drivers/char/random.c b/drivers/char/random.c index d0da5d852d41..b583e5336630 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1818,6 +1818,28 @@ unsigned int get_random_int(void) } EXPORT_SYMBOL(get_random_int); +/* + * Same as get_random_int(), but returns unsigned long. + */ +unsigned long get_random_long(void) +{ + __u32 *hash; + unsigned long ret; + + if (arch_get_random_long(&ret)) + return ret; + + hash = get_cpu_var(get_random_int_hash); + + hash[0] += current->pid + jiffies + random_get_entropy(); + md5_transform(hash, random_int_secret); + ret = *(unsigned long *)hash; + put_cpu_var(get_random_int_hash); + + return ret; +} +EXPORT_SYMBOL(get_random_long); + /* * randomize_range() returns a start address such that * diff --git a/include/linux/random.h b/include/linux/random.h index a75840c1aa71..9c29122037f9 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -34,6 +34,7 @@ extern const struct file_operations random_fops, urandom_fops; #endif unsigned int get_random_int(void); +unsigned long get_random_long(void); unsigned long randomize_range(unsigned long start, unsigned long end, unsigned long len); u32 prandom_u32(void); From 5ef11c35ce86b94bfb878b684de4cdaf96f54b2f Mon Sep 17 00:00:00 2001 From: Daniel Cashman Date: Fri, 26 Feb 2016 15:19:37 -0800 Subject: [PATCH 475/489] mm: ASLR: use get_random_long() Replace calls to get_random_int() followed by a cast to (unsigned long) with calls to get_random_long(). Also address shifting bug which, in case of x86 removed entropy mask for mmap_rnd_bits values > 31 bits. Signed-off-by: Daniel Cashman Acked-by: Kees Cook Cc: "Theodore Ts'o" Cc: Arnd Bergmann Cc: Greg Kroah-Hartman Cc: Catalin Marinas Cc: Will Deacon Cc: Ralf Baechle Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: David S. Miller Cc: Thomas Gleixner Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Al Viro Cc: Nick Kralevich Cc: Jeff Vander Stoep Cc: Mark Salyzyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/mmap.c | 2 +- arch/arm64/mm/mmap.c | 4 ++-- arch/mips/mm/mmap.c | 4 ++-- arch/powerpc/kernel/process.c | 4 ++-- arch/powerpc/mm/mmap.c | 4 ++-- arch/sparc/kernel/sys_sparc_64.c | 2 +- arch/x86/mm/mmap.c | 6 +++--- fs/binfmt_elf.c | 2 +- 8 files changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c index 4b4058db0781..66353caa35b9 100644 --- a/arch/arm/mm/mmap.c +++ b/arch/arm/mm/mmap.c @@ -173,7 +173,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 4c893b5189dd..232f787a088a 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -53,10 +53,10 @@ unsigned long arch_mmap_rnd(void) #ifdef CONFIG_COMPAT if (test_thread_flag(TIF_32BIT)) - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/arch/mips/mm/mmap.c b/arch/mips/mm/mmap.c index 5c81fdd032c3..353037699512 100644 --- a/arch/mips/mm/mmap.c +++ b/arch/mips/mm/mmap.c @@ -146,7 +146,7 @@ unsigned long arch_mmap_rnd(void) { unsigned long rnd; - rnd = (unsigned long)get_random_int(); + rnd = get_random_long(); rnd <<= PAGE_SHIFT; if (TASK_IS_32BIT_ADDR) rnd &= 0xfffffful; @@ -174,7 +174,7 @@ void arch_pick_mmap_layout(struct mm_struct *mm) static inline unsigned long brk_rnd(void) { - unsigned long rnd = get_random_int(); + unsigned long rnd = get_random_long(); rnd = rnd << PAGE_SHIFT; /* 8MB for 32bit, 256MB for 64bit */ diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c index dccc87e8fee5..3c5736e52a14 100644 --- a/arch/powerpc/kernel/process.c +++ b/arch/powerpc/kernel/process.c @@ -1768,9 +1768,9 @@ static inline unsigned long brk_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (long)(get_random_int() % (1<<(23-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT))); else - rnd = (long)(get_random_int() % (1<<(30-PAGE_SHIFT))); + rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT))); return rnd << PAGE_SHIFT; } diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c index 0f0502e12f6c..4087705ba90f 100644 --- a/arch/powerpc/mm/mmap.c +++ b/arch/powerpc/mm/mmap.c @@ -59,9 +59,9 @@ unsigned long arch_mmap_rnd(void) /* 8MB for 32bit, 1GB for 64bit */ if (is_32bit_task()) - rnd = (unsigned long)get_random_int() % (1<<(23-PAGE_SHIFT)); + rnd = get_random_long() % (1<<(23-PAGE_SHIFT)); else - rnd = (unsigned long)get_random_int() % (1<<(30-PAGE_SHIFT)); + rnd = get_random_long() % (1UL<<(30-PAGE_SHIFT)); return rnd << PAGE_SHIFT; } diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c index c690c8e16a96..b489e9759518 100644 --- a/arch/sparc/kernel/sys_sparc_64.c +++ b/arch/sparc/kernel/sys_sparc_64.c @@ -264,7 +264,7 @@ static unsigned long mmap_rnd(void) unsigned long rnd = 0UL; if (current->flags & PF_RANDOMIZE) { - unsigned long val = get_random_int(); + unsigned long val = get_random_long(); if (test_thread_flag(TIF_32BIT)) rnd = (val % (1UL << (23UL-PAGE_SHIFT))); else diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c index 96bd1e2bffaf..72bb52f93c3d 100644 --- a/arch/x86/mm/mmap.c +++ b/arch/x86/mm/mmap.c @@ -71,12 +71,12 @@ unsigned long arch_mmap_rnd(void) if (mmap_is_ia32()) #ifdef CONFIG_COMPAT - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_compat_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); #else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); #endif else - rnd = (unsigned long)get_random_int() & ((1 << mmap_rnd_bits) - 1); + rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 051ea4809c14..7d914c67a9d0 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -653,7 +653,7 @@ static unsigned long randomize_stack_top(unsigned long stack_top) if ((current->flags & PF_RANDOMIZE) && !(current->personality & ADDR_NO_RANDOMIZE)) { - random_variable = (unsigned long) get_random_int(); + random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } From a4a8481ff68a8a324a878e281bc37f18665224f7 Mon Sep 17 00:00:00 2001 From: Guozhonghua Date: Fri, 26 Feb 2016 15:19:40 -0800 Subject: [PATCH 476/489] ocfs2: unlock inode if deleting inode from orphan fails When doing append direct io cleanup, if deleting inode fails, it goes out without unlocking inode, which will cause the inode deadlock. This issue was introduced by commit cf1776a9e834 ("ocfs2: fix a tiny race when truncate dio orohaned entry"). Signed-off-by: Guozhonghua Signed-off-by: Joseph Qi Reviewed-by: Gang He Cc: Mark Fasheh Cc: Joel Becker Cc: Junxiao Bi Cc: [4.2+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ocfs2/aops.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 794fd1587f34..cda0361e95a4 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -956,6 +956,7 @@ clean_orphan: tmp_ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh, update_isize, end); if (tmp_ret < 0) { + ocfs2_inode_unlock(inode, 1); ret = tmp_ret; mlog_errno(ret); brelse(di_bh); From 03cdadb04077b9311bbc67d98cc5401aff76482d Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Fri, 26 Feb 2016 15:19:43 -0800 Subject: [PATCH 477/489] block: disable block device DAX by default The recent *sync enabling discovered that we are inserting into the block_device pagecache counter to the expectations of the dirty data tracking for dax mappings. This can lead to data corruption. We want to support DAX for block devices eventually, but it requires wider changes to properly manage the pagecache. dump_stack+0x85/0xc2 dax_writeback_mapping_range+0x60/0xe0 blkdev_writepages+0x3f/0x50 do_writepages+0x21/0x30 __filemap_fdatawrite_range+0xc6/0x100 filemap_write_and_wait+0x4a/0xa0 set_blocksize+0x70/0xd0 sb_set_blocksize+0x1d/0x50 ext4_fill_super+0x75b/0x3360 mount_bdev+0x180/0x1b0 ext4_mount+0x15/0x20 mount_fs+0x38/0x170 Mark the support broken so its disabled by default, but otherwise still available for testing. Signed-off-by: Dan Williams Signed-off-by: Ross Zwisler Reported-by: Ross Zwisler Suggested-by: Dave Chinner Reviewed-by: Jan Kara Cc: Jens Axboe Cc: Matthew Wilcox Cc: Al Viro Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- block/Kconfig | 13 +++++++++++++ fs/block_dev.c | 6 +++++- 2 files changed, 18 insertions(+), 1 deletion(-) diff --git a/block/Kconfig b/block/Kconfig index 161491d0a879..0363cd731320 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -88,6 +88,19 @@ config BLK_DEV_INTEGRITY T10/SCSI Data Integrity Field or the T13/ATA External Path Protection. If in doubt, say N. +config BLK_DEV_DAX + bool "Block device DAX support" + depends on FS_DAX + depends on BROKEN + help + When DAX support is available (CONFIG_FS_DAX) raw block + devices can also support direct userspace access to the + storage capacity via MMAP(2) similar to a file on a + DAX-enabled filesystem. However, the DAX I/O-path disables + some standard I/O-statistics, and the MMAP(2) path has some + operational differences due to bypassing the page + cache. If in doubt, say N. + config BLK_DEV_THROTTLING bool "Block layer bio throttling support" depends on BLK_CGROUP=y diff --git a/fs/block_dev.c b/fs/block_dev.c index 39b3a174a425..31c6d1090f11 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1201,7 +1201,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_disk = disk; bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; - bdev->bd_inode->i_flags = disk->fops->direct_access ? S_DAX : 0; + if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access) + bdev->bd_inode->i_flags = S_DAX; + else + bdev->bd_inode->i_flags = 0; + if (!partno) { ret = -ENXIO; bdev->bd_part = disk_get_part(disk, partno); From 0a6cf9137ded4856b41910a4336677ee0ffa6736 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:46 -0800 Subject: [PATCH 478/489] ext2, ext4: only set S_DAX for regular inodes When S_DAX is set on an inode we assume that if there are pages attached to the mapping (mapping->nrpages != 0), those pages are clean zero pages that were used to service reads from holes. Any dirty data associated with the inode should be in the form of DAX exceptional entries (mapping->nrexceptional) that is written back via dax_writeback_mapping_range(). With the current code, though, this isn't always true. For example, ext2 and ext4 directory inodes can have S_DAX set, but have their dirty data stored as dirty page cache entries. For these types of inodes, having S_DAX set doesn't really make sense since their I/O doesn't actually happen through the DAX code path. Instead, only allow S_DAX to be set for regular inodes for ext2 and ext4. This allows us to have strict DAX vs non-DAX paths in the writeback code. Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: Theodore Ts'o Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext2/inode.c | 2 +- fs/ext4/inode.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 338eefda70c6..27e2cdd4999b 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -1296,7 +1296,7 @@ void ext2_set_inode_flags(struct inode *inode) inode->i_flags |= S_NOATIME; if (flags & EXT2_DIRSYNC_FL) inode->i_flags |= S_DIRSYNC; - if (test_opt(inode->i_sb, DAX)) + if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode)) inode->i_flags |= S_DAX; } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 9cc57c3b4661..5708e689e63d 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -4155,7 +4155,7 @@ void ext4_set_inode_flags(struct inode *inode) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; - if (test_opt(inode->i_sb, DAX)) + if (test_opt(inode->i_sb, DAX) && S_ISREG(inode->i_mode)) new_fl |= S_DAX; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX); From 73f34a5e2ceddfca27c999c170620e6354aaf6d7 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:49 -0800 Subject: [PATCH 479/489] ext4: online defrag not supported with DAX Online defrag operations for ext4 are hard coded to use the page cache. See ext4_ioctl() -> ext4_move_extents() -> move_extent_per_page() When combined with DAX I/O, which circumvents the page cache, this can result in data corruption. This was observed with xfstests ext4/307 and ext4/308. Fix this by only allowing online defrag for non-DAX files. Signed-off-by: Ross Zwisler Reviewed-by: Jan Kara Cc: Theodore Ts'o Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/ext4/ioctl.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a99b010e2194..eae5917c534e 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -583,6 +583,11 @@ group_extend_out: "Online defrag not supported with bigalloc"); err = -EOPNOTSUPP; goto mext_out; + } else if (IS_DAX(inode)) { + ext4_msg(sb, KERN_ERR, + "Online defrag not supported with DAX"); + err = -EOPNOTSUPP; + goto mext_out; } err = mnt_want_write_file(filp); From 20a90f58997245749c2bdfaea9e51f785ec90d0b Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:52 -0800 Subject: [PATCH 480/489] dax: give DAX clearing code correct bdev dax_clear_blocks() needs a valid struct block_device and previously it was using inode->i_sb->s_bdev in all cases. This is correct for normal inodes on mounted ext2, ext4 and XFS filesystems, but is incorrect for DAX raw block devices and for XFS real-time devices. Instead, rename dax_clear_blocks() to dax_clear_sectors(), and change its arguments to take a bdev and a sector instead of an inode and a block. This better reflects what the function does, and it allows the filesystem and raw block device code to pass in an appropriate struct block_device. Signed-off-by: Ross Zwisler Suggested-by: Dan Williams Reviewed-by: Jan Kara Cc: Theodore Ts'o Cc: Al Viro Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Cc: Ross Zwisler Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/dax.c | 9 ++++----- fs/ext2/inode.c | 6 ++++-- fs/xfs/xfs_aops.c | 2 +- fs/xfs/xfs_aops.h | 1 + fs/xfs/xfs_bmap_util.c | 3 ++- include/linux/dax.h | 2 +- 6 files changed, 13 insertions(+), 10 deletions(-) diff --git a/fs/dax.c b/fs/dax.c index fc2e3141138b..9a173dd8c4a3 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -79,15 +79,14 @@ struct page *read_dax_sector(struct block_device *bdev, sector_t n) } /* - * dax_clear_blocks() is called from within transaction context from XFS, + * dax_clear_sectors() is called from within transaction context from XFS, * and hence this means the stack from this point must follow GFP_NOFS * semantics for all operations. */ -int dax_clear_blocks(struct inode *inode, sector_t block, long _size) +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size) { - struct block_device *bdev = inode->i_sb->s_bdev; struct blk_dax_ctl dax = { - .sector = block << (inode->i_blkbits - 9), + .sector = _sector, .size = _size, }; @@ -109,7 +108,7 @@ int dax_clear_blocks(struct inode *inode, sector_t block, long _size) wmb_pmem(); return 0; } -EXPORT_SYMBOL_GPL(dax_clear_blocks); +EXPORT_SYMBOL_GPL(dax_clear_sectors); /* the clear_pmem() calls are ordered by a wmb_pmem() in the caller */ static void dax_new_buf(void __pmem *addr, unsigned size, unsigned first, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 27e2cdd4999b..4467cbd75f24 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -737,8 +737,10 @@ static int ext2_get_blocks(struct inode *inode, * so that it's not found by another thread before it's * initialised */ - err = dax_clear_blocks(inode, le32_to_cpu(chain[depth-1].key), - 1 << inode->i_blkbits); + err = dax_clear_sectors(inode->i_sb->s_bdev, + le32_to_cpu(chain[depth-1].key) << + (inode->i_blkbits - 9), + 1 << inode->i_blkbits); if (err) { mutex_unlock(&ei->truncate_mutex); goto cleanup; diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index 379c089fb051..fc20518e2398 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -55,7 +55,7 @@ xfs_count_page_state( } while ((bh = bh->b_this_page) != head); } -STATIC struct block_device * +struct block_device * xfs_find_bdev_for_inode( struct inode *inode) { diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h index f6ffc9ae5ceb..a4343c63fb38 100644 --- a/fs/xfs/xfs_aops.h +++ b/fs/xfs/xfs_aops.h @@ -62,5 +62,6 @@ int xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset, struct buffer_head *map_bh, int create); extern void xfs_count_page_state(struct page *, int *, int *); +extern struct block_device *xfs_find_bdev_for_inode(struct inode *); #endif /* __XFS_AOPS_H__ */ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 45ec9e40150c..6c876012b2e5 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -75,7 +75,8 @@ xfs_zero_extent( ssize_t size = XFS_FSB_TO_B(mp, count_fsb); if (IS_DAX(VFS_I(ip))) - return dax_clear_blocks(VFS_I(ip), block, size); + return dax_clear_sectors(xfs_find_bdev_for_inode(VFS_I(ip)), + sector, size); /* * let the block layer decide on the fastest method of diff --git a/include/linux/dax.h b/include/linux/dax.h index 818e45078929..7b6bcedb980f 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -7,7 +7,7 @@ ssize_t dax_do_io(struct kiocb *, struct inode *, struct iov_iter *, loff_t, get_block_t, dio_iodone_t, int flags); -int dax_clear_blocks(struct inode *, sector_t block, long size); +int dax_clear_sectors(struct block_device *bdev, sector_t _sector, long _size); int dax_zero_page_range(struct inode *, loff_t from, unsigned len, get_block_t); int dax_truncate_page(struct inode *, loff_t from, get_block_t); int dax_fault(struct vm_area_struct *, struct vm_fault *, get_block_t, From 7f6d5b529b7dfe2fca30cbf4bc81e16575090025 Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Fri, 26 Feb 2016 15:19:55 -0800 Subject: [PATCH 481/489] dax: move writeback calls into the filesystems Previously calls to dax_writeback_mapping_range() for all DAX filesystems (ext2, ext4 & xfs) were centralized in filemap_write_and_wait_range(). dax_writeback_mapping_range() needs a struct block_device, and it used to get that from inode->i_sb->s_bdev. This is correct for normal inodes mounted on ext2, ext4 and XFS filesystems, but is incorrect for DAX raw block devices and for XFS real-time files. Instead, call dax_writeback_mapping_range() directly from the filesystem ->writepages function so that it can supply us with a valid block device. This also fixes DAX code to properly flush caches in response to sync(2). Signed-off-by: Ross Zwisler Signed-off-by: Jan Kara Cc: Al Viro Cc: Dan Williams Cc: Dave Chinner Cc: Jens Axboe Cc: Matthew Wilcox Cc: Theodore Ts'o Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 13 ++++++++++++- fs/dax.c | 12 +++++++----- fs/ext2/inode.c | 8 ++++++++ fs/ext4/inode.c | 4 ++++ fs/xfs/xfs_aops.c | 4 ++++ include/linux/dax.h | 6 ++++-- mm/filemap.c | 12 ++++-------- 7 files changed, 43 insertions(+), 16 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 31c6d1090f11..826b164a4b5b 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1697,13 +1697,24 @@ static int blkdev_releasepage(struct page *page, gfp_t wait) return try_to_free_buffers(page); } +static int blkdev_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + if (dax_mapping(mapping)) { + struct block_device *bdev = I_BDEV(mapping->host); + + return dax_writeback_mapping_range(mapping, bdev, wbc); + } + return generic_writepages(mapping, wbc); +} + static const struct address_space_operations def_blk_aops = { .readpage = blkdev_readpage, .readpages = blkdev_readpages, .writepage = blkdev_writepage, .write_begin = blkdev_write_begin, .write_end = blkdev_write_end, - .writepages = generic_writepages, + .writepages = blkdev_writepages, .releasepage = blkdev_releasepage, .direct_IO = blkdev_direct_IO, .is_dirty_writeback = buffer_check_dirty_writeback, diff --git a/fs/dax.c b/fs/dax.c index 9a173dd8c4a3..711172450da6 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -484,11 +484,10 @@ static int dax_writeback_one(struct block_device *bdev, * end]. This is required by data integrity operations to ensure file data is * on persistent storage prior to completion of the operation. */ -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end) +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc) { struct inode *inode = mapping->host; - struct block_device *bdev = inode->i_sb->s_bdev; pgoff_t start_index, end_index, pmd_index; pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; @@ -499,8 +498,11 @@ int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, if (WARN_ON_ONCE(inode->i_blkbits != PAGE_SHIFT)) return -EIO; - start_index = start >> PAGE_CACHE_SHIFT; - end_index = end >> PAGE_CACHE_SHIFT; + if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL) + return 0; + + start_index = wbc->range_start >> PAGE_CACHE_SHIFT; + end_index = wbc->range_end >> PAGE_CACHE_SHIFT; pmd_index = DAX_PMD_INDEX(start_index); rcu_read_lock(); diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 4467cbd75f24..6bd58e6ff038 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -876,6 +876,14 @@ ext2_direct_IO(struct kiocb *iocb, struct iov_iter *iter, loff_t offset) static int ext2_writepages(struct address_space *mapping, struct writeback_control *wbc) { +#ifdef CONFIG_FS_DAX + if (dax_mapping(mapping)) { + return dax_writeback_mapping_range(mapping, + mapping->host->i_sb->s_bdev, + wbc); + } +#endif + return mpage_writepages(mapping, wbc, ext2_get_block); } diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 5708e689e63d..aee960b1af34 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2478,6 +2478,10 @@ static int ext4_writepages(struct address_space *mapping, trace_ext4_writepages(inode, wbc); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, + wbc); + /* * No pages to write? This is mainly a kludge to avoid starting * a transaction for special inodes like journal inode on last iput() diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c index fc20518e2398..a9ebabfe7587 100644 --- a/fs/xfs/xfs_aops.c +++ b/fs/xfs/xfs_aops.c @@ -1208,6 +1208,10 @@ xfs_vm_writepages( struct writeback_control *wbc) { xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED); + if (dax_mapping(mapping)) + return dax_writeback_mapping_range(mapping, + xfs_find_bdev_for_inode(mapping->host), wbc); + return generic_writepages(mapping, wbc); } diff --git a/include/linux/dax.h b/include/linux/dax.h index 7b6bcedb980f..636dd59ab505 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -52,6 +52,8 @@ static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); } -int dax_writeback_mapping_range(struct address_space *mapping, loff_t start, - loff_t end); + +struct writeback_control; +int dax_writeback_mapping_range(struct address_space *mapping, + struct block_device *bdev, struct writeback_control *wbc); #endif diff --git a/mm/filemap.c b/mm/filemap.c index 23edccecadb0..3461d97ecb30 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -446,7 +446,8 @@ int filemap_write_and_wait(struct address_space *mapping) { int err = 0; - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = filemap_fdatawrite(mapping); /* * Even if the above returned error, the pages may be @@ -482,13 +483,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0; - if (dax_mapping(mapping) && mapping->nrexceptional) { - err = dax_writeback_mapping_range(mapping, lstart, lend); - if (err) - return err; - } - - if (mapping->nrpages) { + if ((!dax_mapping(mapping) && mapping->nrpages) || + (dax_mapping(mapping) && mapping->nrexceptional)) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); /* See comment of filemap_write_and_wait() */ From 1e9d180ba39f42e8ca4a808baef3a3ef034b1c2c Mon Sep 17 00:00:00 2001 From: Ross Zwisler Date: Sat, 27 Feb 2016 14:01:13 -0500 Subject: [PATCH 482/489] ext2, ext4: fix issue with missing journal entry in ext4_dax_mkwrite() As it is currently written ext4_dax_mkwrite() assumes that the call into __dax_mkwrite() will not have to do a block allocation so it doesn't create a journal entry. For a read that creates a zero page to cover a hole followed by a write that actually allocates storage this is incorrect. The ext4_dax_mkwrite() -> __dax_mkwrite() -> __dax_fault() path calls get_blocks() to allocate storage. Fix this by having the ->page_mkwrite fault handler call ext4_dax_fault() as this function already has all the logic needed to allocate a journal entry and call __dax_fault(). Also update the ext2 fault handlers in this same way to remove duplicate code and keep the logic between ext2 and ext4 the same. Reviewed-by: Jan Kara Signed-off-by: Ross Zwisler Signed-off-by: Theodore Ts'o --- fs/ext2/file.c | 19 +------------------ fs/ext4/file.c | 19 ++----------------- 2 files changed, 3 insertions(+), 35 deletions(-) diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 2c88d683cd91..c1400b109805 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -80,23 +80,6 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return ret; } -static int ext2_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct inode *inode = file_inode(vma->vm_file); - struct ext2_inode_info *ei = EXT2_I(inode); - int ret; - - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - down_read(&ei->dax_sem); - - ret = __dax_mkwrite(vma, vmf, ext2_get_block, NULL); - - up_read(&ei->dax_sem); - sb_end_pagefault(inode->i_sb); - return ret; -} - static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) { @@ -124,7 +107,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext2_dax_vm_ops = { .fault = ext2_dax_fault, .pmd_fault = ext2_dax_pmd_fault, - .page_mkwrite = ext2_dax_mkwrite, + .page_mkwrite = ext2_dax_fault, .pfn_mkwrite = ext2_dax_pfn_mkwrite, }; diff --git a/fs/ext4/file.c b/fs/ext4/file.c index 474f1a4d2ca8..4cd318f31cbe 100644 --- a/fs/ext4/file.c +++ b/fs/ext4/file.c @@ -262,23 +262,8 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return result; } -static int ext4_dax_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - int err; - struct inode *inode = file_inode(vma->vm_file); - - sb_start_pagefault(inode->i_sb); - file_update_time(vma->vm_file); - down_read(&EXT4_I(inode)->i_mmap_sem); - err = __dax_mkwrite(vma, vmf, ext4_dax_mmap_get_block, NULL); - up_read(&EXT4_I(inode)->i_mmap_sem); - sb_end_pagefault(inode->i_sb); - - return err; -} - /* - * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_mkwrite() + * Handle write fault for VM_MIXEDMAP mappings. Similarly to ext4_dax_fault() * handler we check for races agaist truncate. Note that since we cycle through * i_mmap_sem, we are sure that also any hole punching that began before we * were called is finished by now and so if it included part of the file we @@ -311,7 +296,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma, static const struct vm_operations_struct ext4_dax_vm_ops = { .fault = ext4_dax_fault, .pmd_fault = ext4_dax_pmd_fault, - .page_mkwrite = ext4_dax_mkwrite, + .page_mkwrite = ext4_dax_fault, .pfn_mkwrite = ext4_dax_pfn_mkwrite, }; #else From b6853f78e763d42c7a158d8de3549c9827c604ab Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Thu, 25 Feb 2016 18:17:38 +0100 Subject: [PATCH 483/489] hpfs: don't truncate the file when delete fails The delete opration can allocate additional space on the HPFS filesystem due to btree split. The HPFS driver checks in advance if there is available space, so that it won't corrupt the btree if we run out of space during splitting. If there is not enough available space, the HPFS driver attempted to truncate the file, but this results in a deadlock since the commit 7dd29d8d865efdb00c0542a5d2c87af8c52ea6c7 ("HPFS: Introduce a global mutex and lock it on every callback from VFS"). This patch removes the code that tries to truncate the file and -ENOSPC is returned instead. If the user hits -ENOSPC on delete, he should try to delete other files (that are stored in a leaf btree node), so that the delete operation will make some space for deleting the file stored in non-leaf btree node. Reported-by: Al Viro Signed-off-by: Mikulas Patocka Cc: stable@vger.kernel.org # 2.6.39+ Signed-off-by: Al Viro --- fs/hpfs/namei.c | 31 +++---------------------------- 1 file changed, 3 insertions(+), 28 deletions(-) diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 506765afa1a3..bb8d67e2740a 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -376,12 +376,11 @@ static int hpfs_unlink(struct inode *dir, struct dentry *dentry) struct inode *inode = d_inode(dentry); dnode_secno dno; int r; - int rep = 0; int err; hpfs_lock(dir->i_sb); hpfs_adjust_length(name, &len); -again: + err = -ENOENT; de = map_dirent(dir, hpfs_i(dir)->i_dno, name, len, &dno, &qbh); if (!de) @@ -401,33 +400,9 @@ again: hpfs_error(dir->i_sb, "there was error when removing dirent"); err = -EFSERROR; break; - case 2: /* no space for deleting, try to truncate file */ - + case 2: /* no space for deleting */ err = -ENOSPC; - if (rep++) - break; - - dentry_unhash(dentry); - if (!d_unhashed(dentry)) { - hpfs_unlock(dir->i_sb); - return -ENOSPC; - } - if (generic_permission(inode, MAY_WRITE) || - !S_ISREG(inode->i_mode) || - get_write_access(inode)) { - d_rehash(dentry); - } else { - struct iattr newattrs; - /*pr_info("truncating file before delete.\n");*/ - newattrs.ia_size = 0; - newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME; - err = notify_change(dentry, &newattrs, NULL); - put_write_access(inode); - if (!err) - goto again; - } - hpfs_unlock(dir->i_sb); - return -ENOSPC; + break; default: drop_nlink(inode); err = 0; From 0fcbf996d848d03573113d83f4e3fb3bcfa5ab5e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Feb 2016 18:53:12 +0100 Subject: [PATCH 484/489] fs: return -EOPNOTSUPP if clone is not supported -EBADF is a rather confusing error if an operations is not supported, and nfsd gets rather upset about it. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- fs/read_write.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/fs/read_write.c b/fs/read_write.c index 0c8782aa3d71..dadf24e5c95b 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1533,10 +1533,12 @@ int vfs_clone_file_range(struct file *file_in, loff_t pos_in, if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || - (file_out->f_flags & O_APPEND) || - !file_in->f_op->clone_file_range) + (file_out->f_flags & O_APPEND)) return -EBADF; + if (!file_in->f_op->clone_file_range) + return -EOPNOTSUPP; + ret = clone_verify_area(file_in, pos_in, len, false); if (ret) return ret; From c80567c82ae4814a41287618e315a60ecf513be6 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:17:33 -0500 Subject: [PATCH 485/489] do_last(): don't let a bogus return value from ->open() et.al. to confuse us ... into returning a positive to path_openat(), which would interpret that as "symlink had been encountered" and proceed to corrupt memory, etc. It can only happen due to a bug in some ->open() instance or in some LSM hook, etc., so we report any such event *and* make sure it doesn't trick us into further unpleasantness. Cc: stable@vger.kernel.org # v3.6+, at least Signed-off-by: Al Viro --- fs/namei.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/namei.c b/fs/namei.c index f624d132e01e..e30deefad8f8 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3273,6 +3273,10 @@ opened: goto exit_fput; } out: + if (unlikely(error > 0)) { + WARN_ON(1); + error = -EINVAL; + } if (got_write) mnt_drop_write(nd->path.mnt); path_put(&save_parent); From d4565649b6d6923369112758212b851adc407f0c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:23:16 -0500 Subject: [PATCH 486/489] namei: ->d_inode of a pinned dentry is stable only for positives both do_last() and walk_component() risk picking a NULL inode out of dentry about to become positive, *then* checking its flags and seeing that it's not negative anymore and using (already stale by then) value they'd fetched earlier. Usually ends up oopsing soon after that... Cc: stable@vger.kernel.org # v3.13+ Signed-off-by: Al Viro --- fs/namei.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index e30deefad8f8..e0881c0bd228 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1743,11 +1743,11 @@ static int walk_component(struct nameidata *nd, int flags) if (err < 0) return err; - inode = d_backing_inode(path.dentry); seq = 0; /* we are already out of RCU mode */ err = -ENOENT; if (d_is_negative(path.dentry)) goto out_path_put; + inode = d_backing_inode(path.dentry); } if (flags & WALK_PUT) @@ -3192,12 +3192,12 @@ retry_lookup: return error; BUG_ON(nd->flags & LOOKUP_RCU); - inode = d_backing_inode(path.dentry); seq = 0; /* out of RCU mode, so the value doesn't matter */ if (unlikely(d_is_negative(path.dentry))) { path_to_nameidata(&path, nd); return -ENOENT; } + inode = d_backing_inode(path.dentry); finish_lookup: if (nd->depth) put_link(nd); From a7f775428b8f5808815c0e3004020cedb94cbe3b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:31:01 -0500 Subject: [PATCH 487/489] should_follow_link(): validate ->d_seq after having decided to follow ... otherwise d_is_symlink() above might have nothing to do with the inode value we've got. Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Al Viro --- fs/namei.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/namei.c b/fs/namei.c index e0881c0bd228..65a0e9d1ea48 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1712,6 +1712,11 @@ static inline int should_follow_link(struct nameidata *nd, struct path *link, return 0; if (!follow) return 0; + /* make sure that d_is_symlink above matches inode */ + if (nd->flags & LOOKUP_RCU) { + if (read_seqcount_retry(&link->dentry->d_seq, seq)) + return -ECHILD; + } return pick_link(nd, link, inode, seq); } From 5129fa482b16615fd4464d2f5d23acb1b7056c66 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 27 Feb 2016 19:37:37 -0500 Subject: [PATCH 488/489] do_last(): ELOOP failure exit should be done after leaving RCU mode ... or we risk seeing a bogus value of d_is_symlink() there. Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Al Viro --- fs/namei.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/fs/namei.c b/fs/namei.c index 65a0e9d1ea48..9c590e0f66e9 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3211,11 +3211,6 @@ finish_lookup: if (unlikely(error)) return error; - if (unlikely(d_is_symlink(path.dentry)) && !(open_flag & O_PATH)) { - path_to_nameidata(&path, nd); - return -ELOOP; - } - if ((nd->flags & LOOKUP_RCU) || nd->path.mnt != path.mnt) { path_to_nameidata(&path, nd); } else { @@ -3234,6 +3229,10 @@ finish_open: return error; } audit_inode(nd->name, nd->path.dentry, 0); + if (unlikely(d_is_symlink(nd->path.dentry)) && !(open_flag & O_PATH)) { + error = -ELOOP; + goto out; + } error = -EISDIR; if ((open_flag & O_CREAT) && d_is_dir(nd->path.dentry)) goto out; From fc77dbd34c5c99bce46d40a2491937c3bcbd10af Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 28 Feb 2016 08:41:20 -0800 Subject: [PATCH 489/489] Linux 4.5-rc6 --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index fbe1b921798f..af6e5f893d56 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ VERSION = 4 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Blurry Fish Butt # *DOCUMENTATION*